Skip to content
TrustedSkillsbeta
Back to all skills

Mcp Builder

Checked
composiohq·vlatest·agents

Provides MCP tools guidance and assistance for orchestrating AI agents and multi-step workflows.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add composiohq/awesome-claude-skills --skill mcp-builder -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

composiohq

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned composiohq/awesome-claude-skills at be2a406907.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
be2a406907
Manifest
mcp-builder/SKILL.md
Scanned
9 files, 3,891 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

This skill provides a comprehensive guide for building high-quality MCP (Model Context Protocol) servers. These servers enable Large Language Models (LLMs) to interact with external services and APIs, allowing them to accomplish real-world tasks. The skill guides users through a four-phase workflow – research, implementation, review, and evaluation – offering checklists and best practices for each stage. It also includes language-specific implementation guides for Python (FastMCP) and Node/TypeScript.

When to use it

  • When you need to create tools that allow an LLM to access external services or APIs.
  • When designing AI agent workflows beyond simple API endpoint calls, focusing on consolidating related operations into high-impact tools.
  • When optimizing tool responses for limited context windows within the LLM.
  • When developing MCP servers in either Python (using FastMCP) or Node/TypeScript and needing SDK documentation and project structure templates.

Key capabilities

  • Four-phase workflow guide: Research, Implementation, Review, Evaluation.
  • Agent-centric design principles for tool creation.
  • Language-specific implementation guides for Python (FastMCP) and Node/TypeScript.
  • Tool design patterns including input validation, response formatting, pagination, error handling, and annotations.

Example prompts

  • "Guide me through the research phase of building an MCP server."
  • "What are some best practices for optimizing tool responses within a limited context window?"
  • "Show me the project structure template for a Node/TypeScript MCP server."

Tips & gotchas

  • This skill focuses on building MCP servers, not using them. It's geared towards developers creating tools for LLMs.
  • Prioritize designing tools that enable complete workflows rather than just wrapping existing API endpoints.
  • Be mindful of the limited context windows in LLMs and strive to return concise, high-signal information.