Skip to content
TrustedSkillsbeta
Back to all skills

Mcp Builder

Checked
letta-ai·vlatest·agents

Helps with AI, MCP tools as part of orchestrating AI agents and multi-step workflows 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 letta-ai/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

letta-ai

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 letta-ai/skills at b03323bfe9.

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

Commit
b03323bfe9
Manifest
tools/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 assists in developing high-quality MCP (Model Context Protocol) servers, which enable Large Language Models (LLMs) to interact with external services and APIs. It guides users through a structured process of designing tools that facilitate LLMs accomplishing real-world tasks by focusing on workflow optimization and adhering to agent-centric design principles. The skill emphasizes building thoughtful workflows rather than simply wrapping existing API endpoints.

When to use it

  • When you need to create tools for AI agents that go beyond simple API calls, enabling complete task execution.
  • When designing APIs for LLMs where context window limitations are a key consideration.
  • When developing MCP servers and needing guidance on best practices and protocol adherence.

Key capabilities

  • Agent-Centric Design Principles: Provides guidelines for building tools that consider workflows, limited context, actionable error messages, and natural task subdivisions.
  • MCP Protocol Documentation Access: Facilitates loading the official MCP specification from https://modelcontextprotocol.io/llms-full.txt.
  • Framework Documentation Access: Guides users to load relevant documentation for Python (https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md) and TypeScript implementations.
  • Evaluation-Driven Development: Encourages creating evaluation scenarios and iterating based on agent performance feedback.

Example prompts

  • "Guide me through the first phase of MCP server development, focusing on agent-centric design principles."
  • "Load the latest MCP protocol documentation."
  • "Show me the Python SDK documentation for MCP servers."

Tips & gotchas

  • The skill emphasizes a structured four-phase process; follow these steps for optimal results.
  • Pay close attention to context window limitations when designing tools – prioritize high-signal information.
  • Use WebFetch to load external resources as instructed within the guide.