MCP server · API

PMCP MCP gateway

Lets your AI reach dozens of outside tools without slowing down or running out of room.

PMCP is a helper that sits between your AI assistant and all the other tools it can plug into, like GitHub, Jira, or databases. Instead of loading every tool up front, it shows a short menu and only fetches the details when a tool is actually used. It is handy for developers and teams whose AI assistant keeps complaining about too many tools or a full context.

What is an MCP server? The 30-second version

On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to another app or service. This one connects your AI to many services at once, like GitHub and Jira, through a single doorway. When you ask for something, the AI uses this helper to reach the right service for you.

What this MCP server does

You ask your AI a question or give it a task. The AI talks to PMCP instead of talking to every tool directly. PMCP shows a short list of what it can do, and only when a tool is really needed does it fetch the full details. Then it passes your request to the right service, like GitHub or a database, and brings the answer back. You get the result in your chat, and your AI stays fast because it is not carrying every tool description all the time.

Flow diagram: you ask your AI “Find open pull requests in our GitHub repo”, the PMCP MCP gateway reaches GitHub, Jira, Database and Slack, and you get back answer in your chat.

Click to zoom

What you can do with it

Reach many outside services through one connection
Load a tool only when it is actually used
Add a new service without restarting your assistant
Keep a steady set of about 26 helper tools instead of a shifting pile
Cap output size and optionally hide secret values
Start Playwright and Context7 automatically if you list them
Work without an API key for basic capability matching

Try asking your AI

“Find the open pull requests in our GitHub repo and summarize them”
“What is the status of the Jira ticket about the login bug”
“Which database tables have a column called customer_id”
“Add a new MCP server for Slack so I can search messages”

What it gives back to you

You get answers in your chat, like a summary of pull requests, a ticket status, or a list of matching tables. PMCP can also report what tools it loaded or started, and it can make changes in the connected services when you ask. The reply is plain text or a short list, not a file, unless the service itself sends one.

Before you start

What you need

Python installed on your computer
The uv tool (recommended) or pip
An AI assistant that supports MCP, like Claude Code or Codex
A config file for your assistant, which pmcp setup can generate for you

Good to know

If you run it as a shared HTTP service, it is open by default, so set a secret token and use TLS before letting anyone outside your computer reach it.

Install it with your AI

Add PMCP MCP gateway to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check PMCP MCP gateway, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.