Skip to content
TrustedSkillsbeta
Back to all skills

Mcp Builder

Official
anthropics·vlatest·agents

Official anthropics skill for MCP tools — helps with 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 anthropics/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

anthropics

Matched to the vendor's own GitHub organisation.

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 anthropics/skills at dbd4588f9e.

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

Commit
dbd4588f9e
Manifest
skills/mcp-builder/SKILL.md
Scanned
9 files, 3,176 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

The Mcp Builder skill provides a comprehensive guide for developing high-quality MCP (Model Context Protocol) servers. These servers enable Large Language Models (LLMs) to interact with external services through well-defined tools, ultimately allowing agents to accomplish real-world tasks. The skill focuses on best practices across four phases: research, implementation, testing, and evaluation, with specific guidance for TypeScript and Python development. It emphasizes API coverage and clear tool naming over complex workflow tools.

When to use it

  • When building an MCP server to connect LLMs to external services.
  • If you want to ensure your MCP server enables effective agent performance on real-world tasks.
  • For developers using TypeScript or Python to implement MCP servers and seeking best practices.
  • When needing a structured evaluation framework for validating the effectiveness of your MCP server with an LLM.

Key capabilities

  • Four-phase workflow (research, implementation, testing, evaluation) for building MCP servers.
  • Guidance on balancing API coverage versus specialized workflow tools.
  • Best practices for clear and consistent tool naming conventions using prefixes.
  • Recommendations for input/output schemas, pagination, response formatting, and tool annotations (readOnly, destructive, idempotent, openWorld hints).
  • An evaluation framework requiring 10 complex questions with verifiable XML answers to validate LLM effectiveness.

Example prompts

  • "Guide me through the research phase of building an MCP server."
  • "What are best practices for naming tools in my MCP server?"
  • "Show me code examples for implementing pagination in a TypeScript MCP tool."

Tips & gotchas

  • Prioritize comprehensive API coverage over workflow tools when unsure, as performance varies by client.
  • The evaluation framework requires creating 10 independent, read-only questions with verifiable answers in XML format to properly assess your server's effectiveness.
  • Consistent tool naming and clear descriptions are crucial for agent discoverability and efficient operation.