Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Build an MCP server from an OpenAPI spec · mcp-use | DecimalAI

Agent Toolingby mcp-use

Build an MCP server from an OpenAPI spec

Build and deploy an MCP server from an OpenAPI / Swagger spec using the mcp-use TypeScript SDK.

Never made a case worseMaintained

SkillScore

SkillScore78/100

Test results 78

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

22%78%of test cases passed +57 pts

Without skill5 of 23

With skill18 of 23

13 fixed5 passed either way5 still failing0 broke

Model 9/9/2026v4 · latest is v520 comparable

This benchmark measured an earlier version of the skill.

A newer attempt on gemini-3.8-flash on 10/23/2026 did not produce a publishable comparison (graded differently). The snapshot above is the previously measured run.

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskThe user chose to deploy their generated MCP server to mcp-use cloud using `npm run deploy`. What version control setup must exist locally before running the deploy command?

Without the skillMissed

With the skillPassed

Same model, same task. Answers are capped and redacted.

Use this skill

Your agent runs on

Adds every file the skill has, pinned so you can update it. No account needed.

pip install "decimalai>=0.15"
decimalai skills add mcp-use-openapi-to-mcp
claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"

The same install from Python, for a notebook or a setup script.

Install

pip install "decimalai>=0.15"

Add the skill

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("mcp-use-openapi-to-mcp")
if result.exit_code:
    raise SystemExit(result.problems)

print("Added. Start Claude Code with the command below.")

Start Claude Code with it

claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"

Type these in a Claude Code session. No account or API key. It writes the skill and any files it bundles, and asks first when its safety rating isn't Passed.

Add the DecimalAI plugin, once

/plugin marketplace add decimal-labs/decimalai-claude-plugins
/plugin install decimalai@decimalai

Install this skill

/decimalai:install mcp-use-openapi-to-mcp

The plugin needs python3 and curl on your machine.

No Python or account. Claude Code picks it up in its next session.

Save it into your project

curl -fsSL --create-dirs -o .claude/skills/mcp-use-openapi-to-mcp/SKILL.md https://app.decimal.ai/s/mcp-use-openapi-to-mcp/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/mcp-use-openapi-to-mcp/SKILL.md

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Claude Code docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[claude-agent-sdk]"
decimalai skills add mcp-use-openapi-to-mcp

Add it to your agent

import asyncio

from claude_agent_sdk import ClaudeAgentOptions
from decimalai.claude_agent_sdk import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

async def main():
    question = "Hello!"
    async with support.run(question) as run:  # one user message, one run
        async for message in run.query(options=ClaudeAgentOptions(max_turns=6)):
            print(message)

# In a notebook or async code: await main()
asyncio.run(main())

Prefer its own loader? ClaudeAgentOptions(plugins=[skills_plugin()], skills="all") reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

The same install from Python, for a notebook or a setup script. agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[claude-agent-sdk]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("mcp-use-openapi-to-mcp")
if result.exit_code:
    raise SystemExit(result.problems)

import asyncio

from claude_agent_sdk import ClaudeAgentOptions
from decimalai.claude_agent_sdk import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

async def main():
    question = "Hello!"
    async with support.run(question) as run:  # one user message, one run
        async for message in run.query(options=ClaudeAgentOptions(max_turns=6)):
            print(message)

# In a notebook or async code: await main()
asyncio.run(main())

Prefer its own loader? ClaudeAgentOptions(plugins=[skills_plugin()], skills="all") reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/mcp-use-openapi-to-mcp/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from claude_agent_sdk import ClaudeAgentOptions, query

skill = Path(".agents/skills/mcp-use-openapi-to-mcp/SKILL.md").read_text()
options = ClaudeAgentOptions(system_prompt=f"You are a helpful agent.\n\n{skill}", max_turns=6)

async def main():
    async for message in query(prompt="Hello!", options=options):
        print(message)

# In a notebook or async code: await main()
asyncio.run(main())

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Claude Agent SDK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[openai-agents]"
decimalai skills add mcp-use-openapi-to-mcp

Add it to your agent

from agents import Agent, Runner
from decimalai.openai_agents import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    name=support.name,
    instructions=support.instructions,  # your prompt, then the skill list
    tools=[*support.tools],             # your tools, then load_skill
)
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

Using SandboxAgent? capabilities=[Shell(), decimalai.openai_agents.sandbox_skills()] points its own loader at the same folder.

Install

pip install "decimalai[openai-agents]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("mcp-use-openapi-to-mcp")
if result.exit_code:
    raise SystemExit(result.problems)

from agents import Agent, Runner
from decimalai.openai_agents import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    name=support.name,
    instructions=support.instructions,  # your prompt, then the skill list
    tools=[*support.tools],             # your tools, then load_skill
)
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

Using SandboxAgent? capabilities=[Shell(), decimalai.openai_agents.sandbox_skills()] points its own loader at the same folder.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/mcp-use-openapi-to-mcp/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/mcp-use-openapi-to-mcp/SKILL.md").read_text()
agent = Agent(name="support", instructions=f"You are a helpful agent.\n\n{skill}")
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

OpenAI Agents docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[openai]"
decimalai skills add mcp-use-openapi-to-mcp

Add it to your agent

import json

from openai import OpenAI
from decimalai.openai import agent_config

client = OpenAI()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your tools, as Chat Completions takes them, and what answers each.
TOOLS = [{"type": "function", "function": {
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters": {"type": "object", "properties": {"order_id": {"type": "string"}},
                   "required": ["order_id"]},
}}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    # run.system is your prompt, then the skill list.
    messages = [{"role": "system", "content": run.system}, run.message]
    while True:
        reply = client.chat.completions.create(
            model="gpt-5.4-mini",
            messages=messages,
            tools=[*TOOLS, *run.tools],  # your tools, then load_skill
        ).choices[0].message
        messages.append(reply)
        if not reply.tool_calls:
            break
        for call in reply.tool_calls:
            # load_skill is answered by the run; your own tools by FUNCTIONS.
            function = FUNCTIONS.get(call.function.name)
            messages.append(run.tool_result(call) or {
                "role": "tool", "tool_call_id": call.id,
                "content": function(**json.loads(call.function.arguments)) if function
                else f"There is no tool named {call.function.name!r}.",
            })
print(reply.content)

# The Responses API takes run.response_tools instead of run.tools.

Install

pip install "decimalai[openai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("mcp-use-openapi-to-mcp")
if result.exit_code:
    raise SystemExit(result.problems)

import json

from openai import OpenAI
from decimalai.openai import agent_config

client = OpenAI()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your tools, as Chat Completions takes them, and what answers each.
TOOLS = [{"type": "function", "function": {
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters": {"type": "object", "properties": {"order_id": {"type": "string"}},
                   "required": ["order_id"]},
}}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    # run.system is your prompt, then the skill list.
    messages = [{"role": "system", "content": run.system}, run.message]
    while True:
        reply = client.chat.completions.create(
            model="gpt-5.4-mini",
            messages=messages,
            tools=[*TOOLS, *run.tools],  # your tools, then load_skill
        ).choices[0].message
        messages.append(reply)
        if not reply.tool_calls:
            break
        for call in reply.tool_calls:
            # load_skill is answered by the run; your own tools by FUNCTIONS.
            function = FUNCTIONS.get(call.function.name)
            messages.append(run.tool_result(call) or {
                "role": "tool", "tool_call_id": call.id,
                "content": function(**json.loads(call.function.arguments)) if function
                else f"There is no tool named {call.function.name!r}.",
            })
print(reply.content)

# The Responses API takes run.response_tools instead of run.tools.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/mcp-use-openapi-to-mcp/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/mcp-use-openapi-to-mcp/SKILL.md").read_text()
reply = client.chat.completions.create(
    model="gpt-5.4-mini",
    messages=[
        {"role": "system", "content": f"You are a helpful agent.\n\n{skill}"},
        {"role": "user", "content": "Hello!"},
    ],
).choices[0].message

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

OpenAI SDK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[anthropic]"
decimalai skills add mcp-use-openapi-to-mcp

Add it to your agent

import anthropic
from decimalai.anthropic import agent_config

client = anthropic.Anthropic()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

question = "Hello!"
with support.run(question) as run:  # one user message, one run
    answer = client.beta.messages.tool_runner(
        model="claude-haiku-5-5",
        max_tokens=4096,
        system=run.system,     # your prompt, then the skill list
        tools=[*run.tools],    # your tools, then load_skill
        messages=[{"role": "user", "content": question}],
    ).until_done()

Install

pip install "decimalai[anthropic]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("mcp-use-openapi-to-mcp")
if result.exit_code:
    raise SystemExit(result.problems)

import anthropic
from decimalai.anthropic import agent_config

client = anthropic.Anthropic()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

question = "Hello!"
with support.run(question) as run:  # one user message, one run
    answer = client.beta.messages.tool_runner(
        model="claude-haiku-5-5",
        max_tokens=4096,
        system=run.system,     # your prompt, then the skill list
        tools=[*run.tools],    # your tools, then load_skill
        messages=[{"role": "user", "content": question}],
    ).until_done()

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/mcp-use-openapi-to-mcp/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/mcp-use-openapi-to-mcp/SKILL.md").read_text()
reply = client.messages.create(
    model="claude-haiku-5-5",
    max_tokens=4096,
    system=f"You are a helpful agent.\n\n{skill}",
    messages=[{"role": "user", "content": "Hello!"}],
)

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Anthropic docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[google-genai]"
decimalai skills add mcp-use-openapi-to-mcp

Add it to your agent

from google import genai
from google.genai import types
from decimalai.google_genai import agent_config

client = genai.Client()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your functions, as declarations for the model, and what answers each.
TOOLS = [{"function_declarations": [{
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters_json_schema": {"type": "object", "properties": {"order_id": {"type": "string"}},
                               "required": ["order_id"]},
}]}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    config = types.GenerateContentConfig(
        system_instruction=run.system,     # your prompt, then the skill list
        tools=[*TOOLS, *run.tool_params],  # your functions, then load_skill
    )
    contents = [{"role": "user", "parts": [{"text": run.message}]}]
    while True:
        response = client.models.generate_content(
            model="gemini-3.5-flash", contents=contents, config=config,
        )
        if not response.function_calls:
            break
        contents.append(response.candidates[0].content)
        parts = []
        for call in response.function_calls:
            # load_skill is answered by the run; your own functions by FUNCTIONS.
            # A loop of your own rather than automatic function calling, which
            # raises KeyError when the model asks for a function you did not pass.
            function = FUNCTIONS.get(call.name)
            parts.append(run.tool_result(call) or {"function_response": {
                "name": call.name, "id": call.id,
                "response": {"result": function(**(call.args or {})) if function
                             else f"There is no function named {call.name!r}."},
            }})
        contents.append({"role": "user", "parts": parts})
print(response.text)

Install

pip install "decimalai[google-genai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("mcp-use-openapi-to-mcp")
if result.exit_code:
    raise SystemExit(result.problems)

from google import genai
from google.genai import types
from decimalai.google_genai import agent_config

client = genai.Client()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your functions, as declarations for the model, and what answers each.
TOOLS = [{"function_declarations": [{
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters_json_schema": {"type": "object", "properties": {"order_id": {"type": "string"}},
                               "required": ["order_id"]},
}]}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    config = types.GenerateContentConfig(
        system_instruction=run.system,     # your prompt, then the skill list
        tools=[*TOOLS, *run.tool_params],  # your functions, then load_skill
    )
    contents = [{"role": "user", "parts": [{"text": run.message}]}]
    while True:
        response = client.models.generate_content(
            model="gemini-3.5-flash", contents=contents, config=config,
        )
        if not response.function_calls:
            break
        contents.append(response.candidates[0].content)
        parts = []
        for call in response.function_calls:
            # load_skill is answered by the run; your own functions by FUNCTIONS.
            # A loop of your own rather than automatic function calling, which
            # raises KeyError when the model asks for a function you did not pass.
            function = FUNCTIONS.get(call.name)
            parts.append(run.tool_result(call) or {"function_response": {
                "name": call.name, "id": call.id,
                "response": {"result": function(**(call.args or {})) if function
                             else f"There is no function named {call.name!r}."},
            }})
        contents.append({"role": "user", "parts": parts})
print(response.text)

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/mcp-use-openapi-to-mcp/SKILL.md

Give it to your agent

from pathlib import Path
from google import genai
from google.genai import types

client = genai.Client()
skill = Path(".agents/skills/mcp-use-openapi-to-mcp/SKILL.md").read_text()
response = client.models.generate_content(
    model="gemini-3.5-flash",
    contents="Hello!",
    config=types.GenerateContentConfig(system_instruction=f"You are a helpful agent.\n\n{skill}"),
)

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Gemini API docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[langchain]" langchain-openai
decimalai skills add mcp-use-openapi-to-mcp

Add it to your agent

from langchain.agents import create_agent
from decimalai.langchain import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = create_agent(
    "openai:gpt-5.4-mini",
    tools=[],                         # your tools; the middleware adds load_skill
    middleware=[support.middleware],  # your prompt, the skill list and load_skill
)
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

Install

pip install "decimalai[langchain]" langchain-openai

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("mcp-use-openapi-to-mcp")
if result.exit_code:
    raise SystemExit(result.problems)

from langchain.agents import create_agent
from decimalai.langchain import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = create_agent(
    "openai:gpt-5.4-mini",
    tools=[],                         # your tools; the middleware adds load_skill
    middleware=[support.middleware],  # your prompt, the skill list and load_skill
)
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/mcp-use-openapi-to-mcp/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/mcp-use-openapi-to-mcp/SKILL.md").read_text()
agent = create_agent("openai:gpt-5.4-mini", tools=[], system_prompt=f"You are a helpful agent.\n\n{skill}")
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

LangChain docs

CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"
decimalai skills add mcp-use-openapi-to-mcp

Add it to your agent

import decimalai.crewai
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                               # your own CrewAI LLM
    skills=decimalai.crewai.skills(),      # the installed folder
    tools=decimalai.crewai.skill_tools(),  # reads a skill's files, runs its scripts
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

The same install from Python, for a notebook or a setup script. CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("mcp-use-openapi-to-mcp")
if result.exit_code:
    raise SystemExit(result.problems)

import decimalai.crewai
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                               # your own CrewAI LLM
    skills=decimalai.crewai.skills(),      # the installed folder
    tools=decimalai.crewai.skill_tools(),  # reads a skill's files, runs its scripts
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

No DecimalAI package. CrewAI's own loader reads the folder, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/mcp-use-openapi-to-mcp/SKILL.md

Give it to your agent

from pathlib import Path
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                         # your own CrewAI LLM
    skills=[Path(".agents/skills")],
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

CrewAI docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[adk]"
decimalai skills add mcp-use-openapi-to-mcp

Add it to your agent

from decimalai.adk import DecimalAIPlugin, agent_config
from google.adk.agents import LlmAgent
from google.adk.apps import App

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = LlmAgent(
    name="support",          # ADK needs a Python identifier
    model="gemini-3.5-flash",
    instruction=support.instruction,  # your prompt, then the skill list
    tools=[*support.tools],           # your tools, then load_skill
)
# DecimalAIPlugin makes each invocation of runners built from this App one trace.
app = App(name="support", root_agent=agent, plugins=[DecimalAIPlugin()])

Prefer ADK's own loader? SkillToolset(skills=decimalai.adk.skills(), ...) reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

Install

pip install "decimalai[adk]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("mcp-use-openapi-to-mcp")
if result.exit_code:
    raise SystemExit(result.problems)

from decimalai.adk import DecimalAIPlugin, agent_config
from google.adk.agents import LlmAgent
from google.adk.apps import App

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = LlmAgent(
    name="support",          # ADK needs a Python identifier
    model="gemini-3.5-flash",
    instruction=support.instruction,  # your prompt, then the skill list
    tools=[*support.tools],           # your tools, then load_skill
)
# DecimalAIPlugin makes each invocation of runners built from this App one trace.
app = App(name="support", root_agent=agent, plugins=[DecimalAIPlugin()])

Prefer ADK's own loader? SkillToolset(skills=decimalai.adk.skills(), ...) reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/mcp-use-openapi-to-mcp/SKILL.md

Give it to your agent

from pathlib import Path
from google.adk.agents import LlmAgent

skill = Path(".agents/skills/mcp-use-openapi-to-mcp/SKILL.md").read_text()
agent = LlmAgent(
    name="support",
    model="gemini-3.5-flash",
    instruction=lambda context: f"You are a helpful agent.\n\n{skill}",
)

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Google ADK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[pydantic-ai]"
decimalai skills add mcp-use-openapi-to-mcp

Add it to your agent

from pydantic_ai import Agent
from decimalai.pydantic_ai import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    "openai:gpt-4o-mini",
    name=support.name,
    tools=[],                 # your tools; the capability adds load_skill
    capabilities=[support],   # your prompt, the skill list and load_skill
)
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

On the Pydantic AI harness, decimalai.pydantic_ai_harness.skills(project) uses its own loader instead.

Install

pip install "decimalai[pydantic-ai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("mcp-use-openapi-to-mcp")
if result.exit_code:
    raise SystemExit(result.problems)

from pydantic_ai import Agent
from decimalai.pydantic_ai import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    "openai:gpt-4o-mini",
    name=support.name,
    tools=[],                 # your tools; the capability adds load_skill
    capabilities=[support],   # your prompt, the skill list and load_skill
)
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

On the Pydantic AI harness, decimalai.pydantic_ai_harness.skills(project) uses its own loader instead.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/mcp-use-openapi-to-mcp/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/mcp-use-openapi-to-mcp/SKILL.md").read_text()
agent = Agent("openai:gpt-4o-mini", instructions=f"You are a helpful agent.\n\n{skill}")
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Pydantic AI docs

Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" deepagents
decimalai skills add mcp-use-openapi-to-mcp

Add it to your agent

import decimalai.deepagents
from deepagents import create_deep_agent

agent = create_deep_agent(model=model, **decimalai.deepagents.skills())
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

The default backend reads files but has no shell. To run a skill's scripts, pass skills(backend=LocalShellBackend(...)).

The same install from Python, for a notebook or a setup script. Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" deepagents

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("mcp-use-openapi-to-mcp")
if result.exit_code:
    raise SystemExit(result.problems)

import decimalai.deepagents
from deepagents import create_deep_agent

agent = create_deep_agent(model=model, **decimalai.deepagents.skills())
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

The default backend reads files but has no shell. To run a skill's scripts, pass skills(backend=LocalShellBackend(...)).

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/mcp-use-openapi-to-mcp/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/mcp-use-openapi-to-mcp/SKILL.md").read_text()
agent = create_deep_agent(model=model, system_prompt=f"You are a helpful agent.\n\n{skill}")
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Deep Agents docs

Its own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" agent-framework
decimalai skills add mcp-use-openapi-to-mcp

Add it to your agent

import asyncio

from agent_framework import Agent
from decimalai.agent_framework import skills

agent = Agent(client=client, instructions="You are a helpful agent.", context_providers=[skills()])
asyncio.run(agent.run("Hello!"))

It caches skills by default, so restart the process after decimalai skills update.

The same install from Python, for a notebook or a setup script. Its own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" agent-framework

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("mcp-use-openapi-to-mcp")
if result.exit_code:
    raise SystemExit(result.problems)

import asyncio

from agent_framework import Agent
from decimalai.agent_framework import skills

agent = Agent(client=client, instructions="You are a helpful agent.", context_providers=[skills()])
asyncio.run(agent.run("Hello!"))

It caches skills by default, so restart the process after decimalai skills update.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/mcp-use-openapi-to-mcp/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/mcp-use-openapi-to-mcp/SKILL.md").read_text()
agent = Agent(client=client, instructions=f"You are a helpful agent.\n\n{skill}")
asyncio.run(agent.run("Hello!"))

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Microsoft Agent Framework docs

Strands' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" strands-agents
decimalai skills add mcp-use-openapi-to-mcp

Add it to your agent

from decimalai.strands import skills
from strands import Agent
from strands.vended_tools import file_editor, shell

agent = Agent(
    model=model,                # always pass one: the default is Amazon Bedrock
    system_prompt="You are a helpful agent.",
    tools=[file_editor, shell],
    plugins=[skills()],
)
agent("Hello!")

Strands loads an agent's skills once, so build the agent again after decimalai skills update.

The same install from Python, for a notebook or a setup script. Strands' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" strands-agents

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("mcp-use-openapi-to-mcp")
if result.exit_code:
    raise SystemExit(result.problems)

from decimalai.strands import skills
from strands import Agent
from strands.vended_tools import file_editor, shell

agent = Agent(
    model=model,                # always pass one: the default is Amazon Bedrock
    system_prompt="You are a helpful agent.",
    tools=[file_editor, shell],
    plugins=[skills()],
)
agent("Hello!")

Strands loads an agent's skills once, so build the agent again after decimalai skills update.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/mcp-use-openapi-to-mcp/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/mcp-use-openapi-to-mcp/SKILL.md").read_text()
agent = Agent(model=model, system_prompt=f"You are a helpful agent.\n\n{skill}")
agent("Hello!")

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Strands docs

Adds every file the skill has, pinned so you can update it. Cursor, Copilot, Cline and Warp read this folder by themselves.

pip install "decimalai>=0.15"
decimalai skills add mcp-use-openapi-to-mcp

No Python or account. Cursor, Copilot, Cline and Warp read this folder by themselves.

Save it into your project

curl -fsSL --create-dirs -o .agents/skills/mcp-use-openapi-to-mcp/SKILL.md https://app.decimal.ai/s/mcp-use-openapi-to-mcp/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/mcp-use-openapi-to-mcp/SKILL.md

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Cursor and other editors docs

Fetch the file and give its text to your model as instructions. No account or package needed.

Get the file

curl -fsSL https://app.decimal.ai/s/mcp-use-openapi-to-mcp/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/mcp-use-openapi-to-mcp.json

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v5 (v4 tested 9/9/2026)
Source: mcp-use/mcp-use ↗
License: MIT

Manage it in DecimalAI

Saved prompts and skills, pinned versions, and traces of this skill in your runs. DecimalAI does not run your agent.

Claude Code reads files from your project, so DecimalAI config does not apply there.

On Claude Agent SDK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On OpenAI Agents: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On OpenAI SDK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Anthropic: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Gemini API: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On LangChain: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On CrewAI: set DECIMAL_API_KEY and add decimalai.init(crewai=True) to record runs and skill use. The skill version stays in your repo.

On Google ADK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Pydantic AI: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Deep Agents: set DECIMAL_API_KEY and add decimalai.init(langchain=True) to record runs and skill use. The skill version stays in your repo.

On Microsoft Agent Framework: set DECIMAL_API_KEY and add decimalai.init(otel=True, agent_name="support") to record runs and skill use. The skill version stays in your repo.

On Strands: set DECIMAL_API_KEY and add decimalai.init(otel=True, agent_name="support") to record runs and skill use. The skill version stays in your repo.

Editors read files from your project, so DecimalAI config does not apply there.

Anywhere else: record a use with decimalai.log_skill_activation() inside a trace.

Use this skill

SKILL.md

Build an MCP server from an OpenAPI spec

Turn an existing REST API — described by an OpenAPI 3.x or Swagger 2.0 document — into an MCP server. Each operation in the spec becomes one MCP tool the LLM can call. The server runs locally for testing and ships to Manufact / mcp-use cloud with one command.

This skill is the end-to-end recipe: scope → ingest spec → map operations → scaffold → generate tools → wire auth → test → deploy.

Core philosophy: the spec is the contract

The OpenAPI document is the source of truth. Tool names, descriptions, parameter shapes, and auth requirements all come from the spec — they should not be invented. This matters because:

The LLM trusts descriptions. If the spec says summary: "Get current weather for a city", that's exactly what the LLM will read when deciding whether to call the tool. Hand-rolled summaries drift; spec-derived summaries stay in sync if the API changes.
Zod schemas mirror OpenAPI schemas. Every parameter — path, query, body — becomes a field in one zod object. Required/optional, enums, min/max, and descriptions all carry over. The LLM uses the schema to figure out what to ask the user for.
Auth lives outside the spec. OpenAPI declares the auth scheme but never the secret. Secrets come from env vars; the spec tells you which env vars to require.

When in doubt, prefer mechanical fidelity to the spec over creativity. The LLM is doing the creative part — talking to the user — and only needs a faithful, well-typed handle on the API.

Process

1. Scope the request (use AskUserQuestion)

Before writing code, lock five things via the AskUserQuestion tool. All five are about the API and what to build — deployment is a separate question we ask later in step 10, when the user can actually evaluate it against a working server.

Spec source: a file path in the workspace, a URL (e.g., https://api.example.com/openapi.json), or pasted into chat. If pasted, save it to openapi.yaml or openapi.json first.
Server base URL: take it from servers[0].url in the spec if present; otherwise ask. Multiple servers entries are common (prod / staging) — confirm which one.
Auth scheme: read components.securitySchemes. If multiple, ask which to use. If the API needs an API key or token, ask which env var should hold it (API_KEY, OPENAI_API_KEY, etc.). Don't ask for the secret itself — never put it in the conversation or commit it.
Operation filter: large specs (Stripe, GitHub) have hundreds of endpoints. Ask whether to expose all operations, a tag (pets, users), or a hand-picked list. Default to "all" for specs under ~30 operations; ask above that. See references/mapping-rules.md for filtering patterns.
Widgets: ask whether any operations should render a widget in the chat (a React component shown inline next to the LLM's reply), or whether this is a pure tools-only server. The default for an OpenAPI wrapper is tools-only — the LLM reads JSON and talks. Pick widgets only when the user wants a richer UI for specific responses (a map for a geocoding endpoint, a chart for a metrics endpoint, a card list for a search result). This answer drives the scaffold template in step 3: tools-only → --template blank, any widgets → --template mcp-apps (which ships the resources/ widget infrastructure pre-wired). If the user wants widgets on most operations, the mcp-apps-builder skill is usually a better fit than this one — flag that and confirm before proceeding.

Don't skip this step. Generating 200 tools the user doesn't need pollutes the LLM's tool list and slows it down.

2. Acquire and dereference the spec

Get the spec into a single dereferenced JSON object on disk. Dereferencing inlines $refs so downstream code never has to chase pointers.

# In the scaffolded project root
npm install @apidevtools/swagger-parser

// scripts/load-spec.ts (run once, manually or as a build step)
import SwaggerParser from "@apidevtools/swagger-parser";
import { writeFileSync } from "node:fs";

const spec = await SwaggerParser.dereference("./openapi.yaml");
writeFileSync("./openapi.dereferenced.json", JSON.stringify(spec, null, 2));

For URL specs, swagger-parser accepts the URL directly. For pasted YAML, write it to openapi.yaml first, then dereference. If the spec is Swagger 2.0, run it through swagger2openapi first (npx swagger2openapi --outfile openapi.yaml swagger.yaml).

Sanity-check the dereferenced file: open it, search for "$ref" — there should be none. If there are, the spec has circular refs and swagger-parser keeps them as-is; treat those refs as opaque object types in zod.

3. Scaffold with `create-mcp-use-app`

Pick the template based on the widget answer from step 1:

# Tools-only (the default for an OpenAPI wrapper)
npx create-mcp-use-app@latest <project-name> --template blank

# Any widgets at all
npx create-mcp-use-app@latest <project-name> --template mcp-apps

Let the scaffold install dependencies and git init — both are useful (npm install runs mcp-use generate-types postinstall, and a git repo is required by npm run deploy later). The skill installs companion coding-agent skills by default too; that's fine.

Verify the template catalog with npx create-mcp-use-app@latest --list-templates if it's been a while — the available set is blank, mcp-server, mcp-apps as of this writing. Use blank for OpenAPI-first servers; mcp-server includes sample tools you'd rip out.

After scaffolding, add the two extra deps the OpenAPI flow needs:

cd <project-name>
npm install @apidevtools/swagger-parser dotenv

What you get from blank (mcp-apps is a superset with resources/ + widget infrastructure):

index.ts at the root with a configured MCPServer instance — name, title, version, description. Commented-out examples for tools, resources, and prompts. Listens on process.env.PORT (default 3000).
package.json with scripts wired to the mcp-use CLI: dev (hot reload + inspector), build, start, deploy. tsx, zod, and typescript are already in dev/regular deps; don't reinstall them.
tsconfig.json pre-configured for ESM ("type": "module").
public/ with a favicon and an SVG icon — served as static assets.
A .git directory and an initial commit.

The scaffold reserves the env var MCP_URL for the MCP server's own public base URL (used for widget asset URLs and similar). That is not the upstream API's base URL — name your upstream var BASE_URL (or API_BASE_URL if you want to be explicit) to avoid stepping on it.

4. Plan project structure

Keep the tree shallow and predictable. The point is that someone reading the project for the first time can find the OpenAPI client, the tool wiring, and the auth in three obvious files.

<project>/
├── index.ts                         # MCPServer + server.tool() registration loop
├── openapi.yaml                     # The original spec (committed)
├── openapi.dereferenced.json        # Dereferenced spec (gitignored; regenerated)
├── src/
│   ├── client.ts                    # fetch-based HTTP client (base URL + auth + error handling)
│   ├── auth.ts                      # Reads env vars, builds the auth header
│   ├── operations.ts                # Loads dereferenced spec, exposes operation metadata
│   └── schema.ts                    # OpenAPI schema → zod converter
├── scripts/
│   └── load-spec.ts                 # Dereference helper (step 2)
├── .env.example                     # Document required env vars (API_KEY, BASE_URL, etc.)
└── package.json

For tiny specs (<10 operations) you can inline client.ts, auth.ts, and operations.ts into index.ts. For anything bigger, split — the LLM works better when each file has one job.

5. Map operations to tools

For every operation in the spec, you produce one server.tool({...}, handler) call. The mapping is mechanical:

OpenAPI field	MCP tool field
`operationId` (preferred) or `${method}_${path}` sluggified	tool `name` (snake_case)
`summary` + `description`	tool `description`
`parameters` (path + query) + `requestBody.content."application/json".schema`	merged zod object → tool `schema`
`responses.200.content."application/json".schema`	optional zod object → tool `outputSchema`
`security` (or root-level fallback)	which auth headers the handler attaches

Read references/mapping-rules.md for the full rules — including how to name tools when operationId is missing, how to handle oneOf / anyOf / nullable types in zod, how to flatten multi-content request bodies, and how to deal with the response-shape gotchas (binary downloads, streaming, paginated lists).

6. Generate the zod schemas

OpenAPI types map to zod as follows. The full converter lives in src/schema.ts — see references/code-templates.md for the implementation. Key choices:

type: string with enum → z.enum([...]). Use the OpenAPI description as the .describe() arg so the LLM sees it.
type: integer / type: number → z.number().int() / z.number(). Carry over minimum, maximum, multipleOf.
type: array → z.array(<itemType>). If minItems / maxItems exist, chain .min() / .max().
type: object → z.object({...}). Required props are non-optional; others wrap in .optional().
oneOf / anyOf → z.union([...]). allOf with object-only members → merge into one z.object.
nullable: true (OpenAPI 3.0) or type: ["string", "null"] (3.1) → .nullable().

Always call .describe(openapi.description ?? openapi.summary ?? "") on every field so the LLM gets human-readable hints when filling args.

7. Build the HTTP client and auth layer

src/client.ts exposes one function: callOperation(operationId, args) → Promise<unknown>. Internally it:

Looks up the operation in the dereferenced spec.
Substitutes path params into the URL template (/users/{id} + {id: 42} → /users/42).
Appends query params as ?key=value.
Adds auth headers from src/auth.ts.
Serializes the request body as JSON (or application/x-www-form-urlencoded if the spec says so).
Sends the request; throws on non-2xx with the server's error body included.
Returns parsed JSON (or text, for non-JSON responses).

src/auth.ts reads from process.env based on the spec's securitySchemes. See references/auth.md for the four common schemes and how each becomes a header. Required env vars belong in .env.example — that's the contract for whoever runs the server later.

8. Wire tools in `index.ts`

The registration loop is small. Pseudocode:

import "dotenv/config";
import { MCPServer, text } from "mcp-use";
import { operations } from "./src/operations";
import { callOperation } from "./src/client";
import { operationToZod } from "./src/schema";

// Keep the MCPServer fields from the example (title, favicon, icons).
// Just adjust `name`, `title`, and `description` to match the API you're wrapping.
const server = new MCPServer({
  name: "<api-name>",
  title: "<API name>",
  version: "1.0.0",
  description: "MCP server wrapping the <API name> REST API",
  favicon: "favicon.ico",
  icons: [{ src: "icon.svg", mimeType: "image/svg+xml", sizes: ["512x512"] }],
});

for (const op of operations) {
  server.tool(
    {
      name: op.toolName,
      description: op.description,
      schema: operationToZod(op),
    },
    async (args) => {
      const result = await callOperation(op.operationId, args);
      return text(typeof result === "string" ? result : JSON.stringify(result, null, 2));
    },
  );
}

// Streamable HTTP transport — the only supported transport for this skill.
// MCP endpoint: POST http://localhost:<port>/mcp
// Inspector:    http://localhost:<port>/mcp/inspector
const PORT = process.env.PORT ? Number(process.env.PORT) : 3000;
server.listen(PORT);

Transport must be streamable HTTP, not stdio. mcp-use's server.listen(port) sets up the streamable-HTTP transport at /mcp — that's the right choice for every server this skill generates. Don't substitute stdio. Stdio servers can't be deployed to Manufact / mcp-use cloud (cloud needs an HTTP endpoint to route traffic to), can't be tested with the online inspector, can't be added as a custom MCP server in ChatGPT or a custom connector in Claude (both connect over HTTPS), and can't be hit with the curl tests in references/testing.md. Stdio is for local CLI-tool MCP servers, which is not what we're building here.

Full templates for each file in references/code-templates.md.

9. Test the server

Start the dev server first — every test in this step assumes it's running:

npm run dev

The log prints the port (default 3000, falls back to 3001 if taken), the MCP URL (http://localhost:<port>/mcp), and the inspector URL. Leave this running in one terminal; use a second terminal for the test commands below.

Then test in two layers. Don't claim "done" until both pass. Full recipes in references/testing.md.

Layer 1 — mcp-use client CLI. This is the first thing to reach for. The mcp-use package ships a CLI that talks streamable HTTP, handles session/auth bookkeeping, and gives a tools list / tools call / interactive loop straight from the terminal. No code, no curl arithmetic.

# Save the dev server under a short name
npx mcp-use client connect dev http://localhost:3000/mcp

# List and describe tools
npx mcp-use client dev tools list
npx mcp-use client dev tools describe <tool_name>

# Call a tool — args are key=value, or pass JSON for complex shapes
npx mcp-use client dev tools call <tool_name> limit=5
npx mcp-use client dev tools call <tool_name> '{"limit": 5, "filter": "active"}'

# REPL mode for fast iteration
npx mcp-use client dev interactive

For CI / scripted tests, add --json and pipe to jq. If tools list returns nothing, your operation filter in index.ts killed everything or openapi.dereferenced.json is missing. If connect itself fails, the dev server isn't running or it's on a different port — drop to curl (see references/testing.md section "Raw protocol debugging") to confirm the endpoint is alive at all.

Layer 2 — Inspector chat (the real LLM loop). Layer 1 proves the server works. The inspector proves the LLM can use it — that the tool description is descriptive enough for the model to pick the right tool, that the zod schema has enough hints to fill args correctly, that the response shape isn't so weird the model can't summarize it.

http://localhost:<PORT>/mcp/inspector?server=http%3A%2F%2Flocalhost%3A<PORT>%2Fmcp&tab=chat

Test both force-invocation ("Use list_pets with limit 5.") and free-form discovery ("Show me the first 5 pets in the store.") — the second is harder and the one that catches description quality.

Test the failure paths in both layers: missing required arg (zod rejection), wrong auth (upstream 401), upstream 5xx (point BASE_URL at a dead port). Both layers should degrade with a clean error, not a server crash.

If you see "Failed to resolve import" or stale tool definitions in either layer: rm -rf .mcp-use && npm run dev.

10. Deploy (ask the user)

The server works locally. Now ask, via AskUserQuestion, whether to deploy it to mcp-use cloud or keep it local. Two options only — no need to enumerate alternatives:

Deploy to mcp-use cloud — publishes the server at a https://<name>.run.mcp-use.com/mcp URL usable from ChatGPT, Claude, and any MCP client. Best when the server will be used by anyone other than the developer's own dev machine.
Keep local — hand back the dev-server URL and stop. Best for prototyping against an internal API, or when the user wants to evaluate the output before committing to a public URL.

If the user picks keep local, you're done — give them the inspector and /mcp URLs from step 9 and skip the rest of this step. Don't push deploy; premature deploys leak credentials and create stale public endpoints.

If the user picks deploy, the blank scaffold already wires npm run deploy to mcp-use deploy. Two commands once they're logged in:

npx mcp-use login
npm run deploy

This currently requires a GitHub repo. If the project isn't on GitHub yet:

gh repo create <org>/<name> --private --source=. --push

After deploy you get a URL like https://<name>.run.mcp-use.com/mcp. Set the same env vars in the Manufact dashboard (the deploy CLI prints the link to the project page) so the production server has the same auth as your local one.

Full deploy walkthrough — including how to wire env vars in the dashboard, how to view logs, and how to set up branch deploys — is in references/deploy.md.

11. Ship checklist

Before declaring done:

.env.example lists every required env var with a short comment.
openapi.dereferenced.json is in .gitignore (regenerate from openapi.yaml).
npm run build passes; npx tsc --noEmit is clean.
The inspector ran every tool you care about against the live API at least once.
The deployed URL responds to curl https://<name>.run.mcp-use.com/mcp with a valid MCP response.
Commit and push.

Critical reference material

Read these when the relevant step lands. Each file is a focused deep-dive — don't load them all upfront.

references/mapping-rules.md — Operation-to-tool mapping rules: naming, parameter merging, response handling, schema edge cases (oneOf/anyOf/allOf, nullable, recursive refs), filtering large specs.
references/code-templates.md — Copy-ready skeletons for index.ts, src/client.ts, src/auth.ts, src/operations.ts, src/schema.ts, scripts/load-spec.ts, .env.example, and tsconfig.json. Each is annotated.
references/auth.md — The four common auth schemes (apiKey, http bearer, http basic, OAuth2 bearer) and how each becomes a header. Includes the OAuth-with-refresh-token pattern.
references/testing.md — Inspector recipe, the .mcp-use stale-cache trap, how to force-invoke a tool, what to check in tool responses, common 4xx/5xx debugging.
references/deploy.md — mcp-use deploy, GitHub setup, env vars in the Manufact dashboard, branch deploys, observability tabs, and how to add the deployed URL as a custom MCP server in ChatGPT or a custom connector in Claude.

Trigger words and aliases

Use this skill whenever the user says anything in the cluster:

"build an MCP server from this OpenAPI spec / Swagger doc"
"turn this API / swagger.json / openapi.yaml into MCP tools"
"wrap [API name] as an MCP server"
"make [Stripe / GitHub / our internal API] callable from Claude"
"expose these endpoints to an LLM"
"I have an OpenAPI spec, generate the MCP server"
Pastes or attaches a .yaml / .json spec and asks for an MCP version
Describes an existing REST API (with a key, base URL, or docs link) and wants LLM access

When NOT to use this skill

The user wants a widget-driven MCP App where most/every tool renders a custom UI in the chat → use mcp-apps-builder instead. This skill can layer a widget on one or two specific tools, but if widgets are the whole point, the other skill is the right starting frame. Confirm with the user during step 1.
The user has no API yet and wants to design one from scratch → that's an API-design task, not an MCP-wrapping task.
The user wants to consume an MCP server as a client (not build one) → different skill / not this one.
The spec is for a GraphQL or gRPC service, not OpenAPI → this skill is OpenAPI-specific; the patterns transfer but the schema converter doesn't.

When it activates

Automatically, when a task matches. Use this skill whenever the user wants to "turn this OpenAPI spec into an MCP server", "make this API usable from Claude/ChatGPT", "wrap this Swagger doc as MCP tools", "expose this REST API to an LLM", "generate MCP tools from a spec", or pastes/attaches an `openapi.yaml`, `openapi.json`, or `swagger.json` and asks for a Claude-compatible version. Trigger even if the user doesn't say "MCP" — if they

About this skill

Automatic

AI Engineer pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v8 — 10/23/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

mcp-use / mcp-use

skills/openapi-to-mcp/SKILL.md

View on GitHub ↗

License MITImported 10/23/2026Version v5Bundled 5 files

Illustrative Want to see what mcp-use/openapi-to-mcp would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Related skills

Skills that do similar work, with their headline benchmark lift.

From the same source and nearby in the catalogue.

Ready to supercharge your AI agents?

SkillScore

Safety

What it changes

Track record

Use this skill

Build an MCP server from an OpenAPI spec

Core philosophy: the spec is the contract

Process

1. Scope the request (use AskUserQuestion)

2. Acquire and dereference the spec

3. Scaffold with create-mcp-use-app

4. Plan project structure

5. Map operations to tools

6. Generate the zod schemas

7. Build the HTTP client and auth layer

8. Wire tools in index.ts

9. Test the server

10. Deploy (ask the user)

11. Ship checklist

Critical reference material

Trigger words and aliases

When NOT to use this skill

When it activates

SkillSafety

Source

Related skills

More in the registry

3. Scaffold with `create-mcp-use-app`

8. Wire tools in `index.ts`