AI Blocks › Connect AI to your tools
Put your API in an MCP server that is signed in, checked and ready to share
Give it an API spec. Get an MCP server with sign-in, a security review and a package.
Turn an API into a safe, installable MCP server is a free AI workflow for the job "Connect AI to your tools". It guides your AI through several skills in order, passing each step's output to the next.
Free · No account · Made by AI Blocks · Level: advanced · Thinking: high
What it does
An MCP server is easy to build and easy to get wrong. A quick wrapper has no sign-in, hands the model every endpoint, and trusts whatever a client sends. Once other people connect to it, those gaps are your gaps. The steps add safety in the order that matters. First it builds the server from your API spec. You save and run it. Then it adds OAuth sign-in so only people you allow can connect. You commit that. Next it reviews the finished server for risks in the connection, sign-in, tool permissions and logging, and lists fixes. You apply the must-fix ones. Last it hosts and packages the server so it can be installed and updated without breaking users.
You give it
- Your API spec (OpenAPI or similar), or the API code
- Which calls should be exposed, and which must not be
- Who should be allowed to connect, and how they sign in
- Where you want to host it (optional)
You get
- An MCP server in Python or TypeScript, with checked tool definitions
- OAuth sign-in built into the server
- A ranked checklist of security fixes, with the riskiest first
- A hosted and packaged server, with health checks, logging and a plan for new versions
Use it when
- You want your AI, or other people's, to use your API through MCP.
- You built a quick MCP server and now others need to connect to it.
- You are about to publish a server and want it checked first.
Steps
- API to MCP server builder: Give it an API spec. Get an MCP server in Python or TypeScript that lets your AI use that API.
- MCP server sign-in builder: Say how people will connect to your MCP server. Get correct OAuth sign-in built into it.
- MCP server hardener: Point it at an MCP server you run. Get a checklist of fixes for transport, auth, access and logging.
- MCP server publisher: Point it at your MCP server. Get it hosted, scaled and packaged so others can install it.
How to use it
- Download the handoff pack. It's a zip with HANDOFF.md and every skill file this workflow uses.
- Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
- Use a test account and test data for the API while you build.
- Do all three of your steps. Each one makes the next check read the real code.