Ready to supercharge your AI agents?

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

MCP Server Development · code-saurabh | DecimalAI

agent toolingby code-saurabh

MCP Server Development

code-saurabh/mcp-builder

Source code-saurabh/openskills ↗License MIT

Build production-grade MCP (Model Context Protocol) servers that connect AI agents to external APIs, databases, and services.

SkillScore91Maintained

Automatic

AI Engineer pack

Last verified 8/4/2026

What it changes

Passed 20 of 22 test cases with the skill, and 13 of 22 without it.

Without skill59%

With skill91%

Checks it passed that the model alone missed

The annotations object sets readOnlyHint to false.
The annotations object sets destructiveHint to true.
Every tool parameter in the Zod schema includes a .describe() call.

and 10 more in the full report

7 fixed13 passed either way2 still failing0 broke

Pass-rate lift: +32 pp
Tokens: +153%
Agent turns: 0%
Response time: -23%

Model gemini-3.6-flashMeasured 8/4/2026v120 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/code-saurabh-mcp-builder/SKILL.md https://app.decimal.ai/s/code-saurabh-mcp-builder/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add code-saurabh-mcp-builder, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/code-saurabh-mcp-builder/ and pins it in .decimal/skills.lock

decimalai skills add code-saurabh-mcp-builder

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/code-saurabh-mcp-builder/SKILL.md https://app.decimal.ai/s/code-saurabh-mcp-builder/SKILL.md

Raw file: /s/code-saurabh-mcp-builder/SKILL.md ↗ · machine-readable summary at /s/code-saurabh-mcp-builder.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 7

Prompt

Before implementing tools defined in a JSON inventory contract file named tools.json, what validation script command should be run to verify the contract?

What was checked, without and with the skill
Checked	Without skill	With skill
The response specifies executing python scripts/validate_tool_contract.py tools.json.	Missed	Passed

case-15 · gemini-3.6-flash · 8/4/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md418 lines3 filesincludes scripts

MCP Server Development

MCP (Model Context Protocol) is the standard for connecting AI agents to external tools and services. An MCP server exposes tools, resources, and prompts that any compatible AI agent can call — Claude, GPT-4, Gemini, or any other model that speaks the protocol.

Build MCP servers like you build APIs: with clear contracts, proper error handling, and the caller (the AI agent) as your user. A badly designed MCP tool confuses the model. A well-designed one makes the model dramatically more capable.

MCP Builder Principles

The AI agent is the caller — design for it. Tool names, descriptions, and schemas must be clear enough that an LLM picks the right tool without being told. If a tool name is ambiguous, the agent will misuse it.
Tool descriptions are prompt engineering. The description field in your tool schema is what the model reads to decide when and how to call it. Write it like a senior engineer explaining an API to a junior — concrete, precise, with examples.
Comprehensive beats clever. Cover the API's core operations completely before adding workflow shortcuts. Agents can compose basic tools; they cannot invent missing operations.
Actionable errors are non-negotiable. When a tool fails, the error message must tell the agent exactly what went wrong and exactly what to try next. "An error occurred" is useless. "Authentication failed: API key missing. Set the X-API-KEY header with your key from https://example.com/settings/api" is useful.
Stateless by default. Design tools to be stateless and idempotent where possible. Stateful MCP servers are harder to debug, scale, and reason about.
Security is not optional. MCP servers run with the credentials of the human user. Never log secrets. Validate every input. Scope permissions to the minimum required.

Step 0: Plan Before You Build

Answer these before writing a line of code:

What service are you wrapping? Name it. What does it do?
What are the 5 most common operations a user needs? Start here — not with full API coverage.
What is the authentication mechanism? API key, OAuth, bearer token, mTLS?
What transport? stdio for local tools (runs on user's machine), streamable HTTP for remote servers (deployed, shareable).
What language? TypeScript recommended (best SDK support, type safety, broad compatibility). Python (FastMCP) for data/ML workflows.
What are the failure modes? API rate limits, network timeouts, auth expiry — plan the error messages now.

Architecture

Transport Selection

Transport	When to use	How it works
stdio	Local tools, developer utilities, file system access	Agent spawns the server as a subprocess; communicates via stdin/stdout
Streamable HTTP	Remote services, shared team servers, deployed APIs	Server runs independently; agent connects via HTTP; stateless JSON preferred

Track record

Benchmark

20 / 22

test cases passed, vs 13 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

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

code-saurabh / openskills

mcp-builder/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1Bundled 2 files · scripts

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

MCP Server Development

MCP Builder Principles

Step 0: Plan Before You Build

Architecture

Transport Selection

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills