About Recurse MCP
Recurse MCP exposes Recurse Center API endpoints as MCP tools for AI-compatible clients. It helps users look up Recursers, batches, and locations, and check who is at the hub, using a personal access token.
Key features
- 01Search Recurse Center members
- 02View member profiles
- 03Check who is at the hub
- 04Look up batches and locations
Use cases
- 01Finding a Recurse Center member profile
- 02Checking who is at the hub
- 03Looking up a batch or location
MCP support
The MCP server exposes Recurse Center API endpoints as tools for MCP-compatible AI assistants. It requires a Recurse Center personal access token.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMERecurse MCP
What's This Thing?
A magical bridge between the Recurse Center's API and AI built by Namanyay (SP2'25)
What Does It Do?
This nifty little server lets AI tools (like Claude or ChatGPT) interact with the Recurse Center API to:
- Find fellow Recursers and
stalkview their profiles - Check who's hanging out at the hub
- Look up batches and locations
Why?
Why not?
Getting Started
- Clone this repo
- Create a
.envfile with your Recurse Center personal access token:RECURSE_PAT=your_token_goes_here - Install dependencies:
npm install - Run the server:
npm start - The server runs on port 9000 by default
How It Works
This project implements the Model Context Protocol (MCP), exposing Recurse Center API endpoints as MCP tools. It works with any MCP-compatible AI assistant.
Your AI can now search for Recursers, check batches, and do other Recurse-y things without needing direct API access.
Requirements
- Node.js
- A Recurse Center API token
- A sense of humor
Disclaimer
This tool was not built to help AIs infiltrate the Recurse Center community and replace all humans with sophisticated bots. Probably.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.