Ready to supercharge your AI agents?

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

Beeper Desktop API · gfsaaser24 | DecimalAI

Codingby gfsaaser24

Beeper Desktop API

Complete reference for the Beeper Desktop API — a local HTTP + WebSocket + MCP server exposed by Beeper Desktop that lets code read, search, send, edit, react to, and stream messages across WhatsApp, iMessage, Telegram, Signal, Twitter/X, Discord, and every other network connected to the Beeper client.

Never made a case worse

SkillScore

SkillScore100/100

Test results 100

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

14%100%of test cases passed +86 pts

Without skill3 of 22

With skill22 of 22

19 fixed3 passed either way0 still failing0 broke

Measured on gemini-3.6-flash8/6/2026v1

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskI want to configure Claude Code to use my running Beeper Desktop server as an MCP tool provider over HTTP. What CLI command should I run?

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 gfsaaser24-beeper-desktop-api
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("gfsaaser24-beeper-desktop-api")
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 gfsaaser24-beeper-desktop-api

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/gfsaaser24-beeper-desktop-api/SKILL.md https://app.decimal.ai/s/gfsaaser24-beeper-desktop-api/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/gfsaaser24-beeper-desktop-api/SKILL.md

This gets SKILL.md only. The skill's 12 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 gfsaaser24-beeper-desktop-api

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("gfsaaser24-beeper-desktop-api")
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/gfsaaser24-beeper-desktop-api/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/gfsaaser24-beeper-desktop-api/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 12 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 gfsaaser24-beeper-desktop-api

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("gfsaaser24-beeper-desktop-api")
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/gfsaaser24-beeper-desktop-api/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/gfsaaser24-beeper-desktop-api/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 12 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 gfsaaser24-beeper-desktop-api

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("gfsaaser24-beeper-desktop-api")
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/gfsaaser24-beeper-desktop-api/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/gfsaaser24-beeper-desktop-api/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 12 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 gfsaaser24-beeper-desktop-api

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("gfsaaser24-beeper-desktop-api")
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/gfsaaser24-beeper-desktop-api/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/gfsaaser24-beeper-desktop-api/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 12 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 gfsaaser24-beeper-desktop-api

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("gfsaaser24-beeper-desktop-api")
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/gfsaaser24-beeper-desktop-api/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/gfsaaser24-beeper-desktop-api/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 12 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 gfsaaser24-beeper-desktop-api

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("gfsaaser24-beeper-desktop-api")
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/gfsaaser24-beeper-desktop-api/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/gfsaaser24-beeper-desktop-api/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 12 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 gfsaaser24-beeper-desktop-api

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("gfsaaser24-beeper-desktop-api")
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/gfsaaser24-beeper-desktop-api/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 12 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 gfsaaser24-beeper-desktop-api

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("gfsaaser24-beeper-desktop-api")
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/gfsaaser24-beeper-desktop-api/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/gfsaaser24-beeper-desktop-api/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 12 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 gfsaaser24-beeper-desktop-api

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("gfsaaser24-beeper-desktop-api")
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/gfsaaser24-beeper-desktop-api/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/gfsaaser24-beeper-desktop-api/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 12 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 gfsaaser24-beeper-desktop-api

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("gfsaaser24-beeper-desktop-api")
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/gfsaaser24-beeper-desktop-api/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/gfsaaser24-beeper-desktop-api/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 12 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 gfsaaser24-beeper-desktop-api

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("gfsaaser24-beeper-desktop-api")
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/gfsaaser24-beeper-desktop-api/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/gfsaaser24-beeper-desktop-api/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 12 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 gfsaaser24-beeper-desktop-api

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("gfsaaser24-beeper-desktop-api")
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/gfsaaser24-beeper-desktop-api/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/gfsaaser24-beeper-desktop-api/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 12 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 gfsaaser24-beeper-desktop-api

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/gfsaaser24-beeper-desktop-api/SKILL.md https://app.decimal.ai/s/gfsaaser24-beeper-desktop-api/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/gfsaaser24-beeper-desktop-api/SKILL.md

This gets SKILL.md only. The skill's 12 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/gfsaaser24-beeper-desktop-api/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/gfsaaser24-beeper-desktop-api.json

This gets SKILL.md only. The skill's 12 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 8/6/2026
Source: gfsaaser24/beeper-desktop-api-skill ↗
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

Beeper Desktop API

Overview

Beeper Desktop ships a local REST + WebSocket + MCP server that lets code interact with every chat network the user has connected — WhatsApp, iMessage, Signal, Telegram, Twitter/X, Discord, Matrix, Instagram, LinkedIn, etc. — through a single unified surface.

Default server: http://localhost:23373 WebSocket: ws://localhost:23373/v1/ws MCP (HTTP stream): http://localhost:23373/v0/mcp MCP (SSE): http://localhost:23373/v0/sse Minimum Beeper Desktop version: 4.1.169+

Prerequisites

Install Beeper Desktop from https://www.beeper.com/download (v4.1.169 or newer).
Open Beeper, go to Settings → Developers → Beeper Desktop API, and enable the server.
In Settings → Developers → Approved connections, click + to create an access token. Save it — you will need it for every request.

Environment variable convention used by the SDKs: BEEPER_ACCESS_TOKEN.

Authentication

All endpoints (REST, WebSocket, and MCP) accept a standard bearer token:

Authorization: Bearer <your_token>

Token acquisition modes:

In-app — Settings → Developers → Approved connections → +.
OAuth 2.0 (PKCE) — Discovery metadata at GET /.well-known/oauth-authorization-server (RFC 8414). The built-in MCP server handles OAuth automatically per the MCP authorization spec. Most clients (Claude Code, Cursor, VS Code, Windsurf, Gemini CLI) go through OAuth automatically when connecting to the HTTP-streamable MCP endpoint.
Token introspection — POST /oauth/introspect with Content-Type: application/x-www-form-urlencoded body token=<token>&token_type_hint=access_token. Returns { active: true, ... } or { active: false }.

When a bearer token is passed to the MCP endpoints (/v0/mcp, /v0/sse), OAuth is bypassed and the token is used directly.

Key concepts

accountID — stable ID for a connected network (e.g. local-whatsapp_ba_EvYDBBsZbRQAy3UOSWqG0LuTVkc). Always use accountID for routing actions. network ("WhatsApp", "Telegram", ...) is display-only.
chatID — room/thread identifier, often in Matrix format (!NCdzlIaMjZUmvmvyHU:beeper.com). Some chats (notably iMessage) don't have durable IDs — use localChatID when surfaced.
messageID — stable per-message ID, suitable for cursor-based pagination and editing/reacting.
Pagination model — cursor-based. Responses return oldestCursor / newestCursor + hasMore. To fetch the next page, pass the appropriate cursor plus direction=before (older) or direction=after (newer). The TS/Python/Go SDKs hide this behind async iterators.
Attachments — upload first to /v1/assets/upload (multipart) or /v1/assets/upload/base64, get back an uploadID, then reference that uploadID in the attachment field of POST /v1/chats/{chatID}/messages.
Asset URLs — mxc://... (remote Matrix content), localmxc://... (local Beeper content), or file://.... Download via POST /v1/assets/download or stream directly via GET /v1/assets/serve?url=... (supports HTTP Range).
Editing — text-only. Messages with attachments cannot be edited.
Versioning — /v1/* is the current RESTful surface. /v0/* is gRPC-style and deprecated (breaking change in Beeper Desktop 4.1.294, 2025-10-16). Always prefer /v1.

SDKs

Language	Package	Install
TypeScript	`@beeper/desktop-api`	`npm install @beeper/desktop-api`
Python	`beeper_desktop_api`	`pip install git+ssh://[email protected]/beeper/desktop-api-python.git`
Go	`github.com/beeper/desktop-api-go`	`go get github.com/beeper/desktop-api-go`
Terraform / Ruby / Java / Kotlin	Listed in docs	—

For complete SDK method maps (every method, every param, every response shape), load:

references/sdk-typescript.md — TS SDK (@beeper/desktop-api)
references/sdk-python.md — Python SDK (sync + async)
references/sdk-go.md — Go SDK

Quick start

curl

export BEEPER_ACCESS_TOKEN="your_token_here"

# 1. Verify the server is up and discover endpoints
curl http://localhost:23373/v1/info \
  -H "Authorization: Bearer $BEEPER_ACCESS_TOKEN"

# 2. List connected networks
curl http://localhost:23373/v1/accounts \
  -H "Authorization: Bearer $BEEPER_ACCESS_TOKEN"

# 3. List chats (paginated)
curl http://localhost:23373/v1/chats \
  -H "Authorization: Bearer $BEEPER_ACCESS_TOKEN"

# 4. Send a message
curl -X POST http://localhost:23373/v1/chats/$CHAT_ID/messages \
  -H "Authorization: Bearer $BEEPER_ACCESS_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"text":"Hello from curl"}'

TypeScript

import BeeperDesktop from '@beeper/desktop-api';

const client = new BeeperDesktop({ accessToken: process.env.BEEPER_ACCESS_TOKEN });

const info = await client.info.retrieve();
const accounts = await client.accounts.list();

// Auto-paginate messages matching a query
for await (const msg of client.messages.search({ query: 'invoice', limit: 50 })) {
  console.log(msg.senderName, msg.text);
}

// Send a reply
await client.messages.send(chatID, { text: 'On it', replyToMessageID: msgID });

Python

from beeper_desktop_api import BeeperDesktop

client = BeeperDesktop()  # reads BEEPER_ACCESS_TOKEN from env

info = client.info.retrieve()
for account in client.accounts.list():
    print(account.network, account.account_id)

for msg in client.messages.search(query="invoice", limit=50):
    print(msg.sender_name, msg.text)

client.messages.send(chat_id, body={"text": "On it", "reply_to_message_id": msg_id})

Go

import (
    "context"
    beeperdesktopapi "github.com/beeper/desktop-api-go"
    "github.com/beeper/desktop-api-go/option"
)

client := beeperdesktopapi.NewClient(
    option.WithAccessToken(os.Getenv("BEEPER_ACCESS_TOKEN")),
)

info, _ := client.Info.Get(context.TODO())
accounts, _ := client.Accounts.List(context.TODO())

REST endpoint summary

Area	Method	Path	Summary
Server	GET	`/v1/info`	Discovery: app/platform/server/endpoints metadata
Accounts	GET	`/v1/accounts`	List connected networks
Chats	GET	`/v1/chats`	List chats (paginated, sorted by last activity)
Chats	POST	`/v1/chats`	Create (`mode=create`) or start (`mode=start`) a chat
Chats	GET	`/v1/chats/{chatID}`	Retrieve chat details
Chats	GET	`/v1/chats/search`	Search chats by title/participants
Chats	POST	`/v1/chats/{chatID}/archive`	Archive / unarchive
Reminders	POST	`/v1/chats/{chatID}/reminders`	Create chat reminder
Reminders	DELETE	`/v1/chats/{chatID}/reminders`	Clear chat reminder
Messages	GET	`/v1/chats/{chatID}/messages`	List messages (cursor pagination)
Messages	POST	`/v1/chats/{chatID}/messages`	Send message (text, attachment, reply)
Messages	PUT	`/v1/chats/{chatID}/messages/{messageID}`	Edit message text
Reactions	POST	`/v1/chats/{chatID}/messages/{messageID}/reactions`	Add reaction
Reactions	DELETE	`/v1/chats/{chatID}/messages/{messageID}/reactions`	Remove reaction
Messages	GET	`/v1/messages/search`	Cross-chat message search with filters
Contacts	GET	`/v1/accounts/{accountID}/contacts`	Search contacts on one account
Contacts	GET	`/v1/accounts/{accountID}/contacts/list`	Paginated contact list
Search	GET	`/v1/search`	Unified search (chats + participants + first page of messages)
Assets	GET	`/v1/assets/serve?url=`	Stream asset (Range-supported)
Assets	POST	`/v1/assets/download`	Download mxc/localmxc to local file URL
Assets	POST	`/v1/assets/upload`	Upload via multipart/form-data
Assets	POST	`/v1/assets/upload/base64`	Upload via JSON base64
App	POST	`/v1/focus`	Focus Beeper Desktop window, optionally open chat/message/draft
OAuth	GET	`/.well-known/oauth-authorization-server`	OAuth 2.0 discovery
OAuth	POST	`/oauth/introspect`	Token introspection

Full parameter, request body, and response schemas for every endpoint are in references/endpoints-rest.md. Always load that file before writing code against a specific endpoint.

Realtime events (WebSocket, experimental)

Connect to ws://localhost:23373/v1/ws with Authorization: Bearer <token>, send a subscriptions.set command, and receive chat.upserted / chat.deleted / message.upserted / message.deleted events. Full protocol + schemas in references/websocket.md.

MCP server

Beeper Desktop ships a built-in MCP server so agents (Claude Code, Cursor, VS Code, Windsurf, Gemini CLI) can search and send messages via MCP tools. Full setup by client in references/mcp-server.md.

Quick add for Claude Code:

claude mcp add beeper http://localhost:23373/v0/mcp -t http -s user

Reference files

Load the relevant file for the task at hand:

references/endpoints-rest.md — every REST endpoint with full request/response schemas, path/query/body params, and curl examples. Load this whenever writing direct HTTP calls or needing exhaustive param detail.
references/sdk-typescript.md — @beeper/desktop-api complete method map, types, options, pagination, error classes.
references/sdk-python.md — beeper_desktop_api sync and async clients, every namespace/method.
references/sdk-go.md — github.com/beeper/desktop-api-go complete method map.
references/schemas.md — shared object types (Account, Chat, Message, Attachment, Reaction, Participant) used everywhere in responses.
references/websocket.md — experimental WebSocket realtime event protocol.
references/mcp-server.md — MCP server setup for every client (Claude Desktop, Claude Code, Cursor, VS Code, Raycast, Windsurf, Warp, Codex, Gemini CLI) plus stdio proxy via @beeper/mcp-remote.
references/remote-access.md — exposing the API to other machines: Advanced Settings toggle, 0.0.0.0 binding, X-Forwarded-Host / X-Forwarded-Proto base-URL derivation, Cloudflare Quick Tunnels setup, and the SSE-over-Cloudflare limitation.
references/bridges-self-hosting.md — bbctl (Beeper Bridge Manager) overview, install/login/run, official bridge identifiers (telegram, whatsapp, signal, discord, slack, gmessages, meta, twitter, bluesky, imessage, linkedin, irc, …), and how self-hosted bridges surface through the Desktop API.
references/authentication.md — in-app vs OAuth, introspection, MCP auth bypass, CORS notes.
references/errors.md — status codes and error response shape.
references/cookbook.md — common recipes (bulk DM, watch a chat, scrape messages to CSV, etc.).

Out of scope (other Beeper developer surfaces)

developers.beeper.com also documents two adjacent surfaces that are NOT part of the Desktop API and therefore not covered by this skill beyond a brief mention here:

Android Content Providers — content://com.beeper.api/{chats,messages,contacts} exposed by Beeper Android under permissions com.beeper.android.permission.READ_PERMISSION / SEND_PERMISSION. Separate API with its own columns, parameters, and change-notification model. Use the official Android docs when building against this.
Android Intents — e.g. com.beeper.android.TOGGLE_INCOGNITO_MODE broadcast (requires Beeper Android ≥ 4.31.1 and a Plus subscription). Android-only.

Guardrails

Never use /v0/*. It is deprecated; use /v1/*. /v0 is preserved only for the MCP endpoint path (/v0/mcp, /v0/sse).
Use accountID, not network, for any write action. network is a display label and changes.
Download asset URLs promptly. srcURL and avatar URLs may be temporary or local-only to the device.
Edits are text-only. PUT /v1/chats/{chatID}/messages/{messageID} fails on messages with attachments.
Rate limits return 429. Back off on 429 and retry with jitter; the SDKs do this automatically when maxRetries > 0.
iMessage quirk. iMessage chats may not expose a stable chatID — the get chat endpoint warns about this. Use localChatID where available.
Cursor opacity. Never inspect or mutate cursor strings. Pass them back verbatim with direction.
Search is literal. query= does literal word matching — NOT semantic search. All words must match.

When it activates

Automatically, when a task matches. Use this skill whenever the user asks to build against the Beeper Desktop API, wire up the Beeper MCP server, send or search messages across chat networks through Beeper, automate Beeper Desktop,

About this skill

Automatic

Coding pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026

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

gfsaaser24 / beeper-desktop-api-skill

skills/beeper-desktop-api/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 12 files

Illustrative Want to see what gfsaaser24/beeper-desktop-api 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

Beeper Desktop API

Overview

Prerequisites

Authentication

Key concepts

SDKs

Quick start

curl

TypeScript

Python

Go

REST endpoint summary

Realtime events (WebSocket, experimental)

MCP server

Reference files

Out of scope (other Beeper developer surfaces)

Guardrails

When it activates

SkillSafety

Source

Related skills

More in the registry