Skip to content
TrustedSkillsbeta
Back to all skills

Mcp Builder

Checked
jezweb·vlatest·agents·MIT

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 jezweb/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

jezweb

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 jezweb/claude-skills at 1260fa7439.

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

Commit
1260fa7439
Manifest
plugins/integrations/skills/mcp-builder/SKILL.md
Scanned
15 files, 3,877 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 enables AI agents to quickly build and deploy Model Context Protocol (MCP) servers in Python using the FastMCP framework. It scaffolds a working server from a description, allowing you to define tools (callable functions), resources (readable data), and prompts (reusable templates). The tool supports local testing modes and deployment options including FastMCP Cloud, Docker, and Cloudflare Workers.

When to use it

  • You need to create an MCP server for Claude AI agents to interact with custom tools or data.
  • You want a rapid way to prototype and deploy simple agent workflows using the Model Context Protocol.
  • You are building a system where Claude needs to call specific functions (tools) or access particular data resources.

Key capabilities

  • Server Scaffolding: Generates a basic Python MCP server structure based on a description of desired functionality.
  • Tool, Resource & Prompt Definition: Supports defining callable tools, readable resources, and reusable prompt templates within the server.
  • Local Testing Modes: Provides options for direct execution, development mode with auto-reload, and HTTP transport for testing.
  • Deployment Options: Enables deployment to FastMCP Cloud, Docker containers, or Cloudflare Workers.
  • Pre-deploy Checklist: Includes a checklist to identify common issues before deploying the server.

Example prompts

  • "Build an MCP server for querying our customer database."
  • "Create an MCP server with a tool that searches customers by name and a resource providing customer details."
  • "Scaffold a FastMCP server with a function called 'search_customers' that takes a query string as input."

Tips & gotchas

  • The generated server instance must be at the module level for deployment to FastMCP Cloud.
  • Install fastmcp using pip install fastmcp before creating the server file.
  • For Claude Code terminal use, companion CLI scripts can be added alongside the MCP server.