About raptr-agent-finder
raptr-agent-finder is an MCP server for ChatGPT workflows around single-file agents. It searches the public RAR registry, provides agent source and validation, and can run an agent in chat.
Key features
- 01Search the public agent registry
- 02Retrieve agent source code
- 03Check agent files against rules
- 04Run an agent in ChatGPT chat
- 05Provide agent templates and run guidance
Use cases
- 01Find an existing agent for a task
- 02Review an agent file before use
- 03Run an agent on data in chat
MCP support
Exposes tools to MCP clients for searching RAR, retrieving and checking agents, and running one in chat. Its endpoint uses streamable HTTP with stateless JSON responses.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://api.airaptr.com/finder/mcpclaude mcp add --transport http com-airaptr-raptr-agent-finder https://api.airaptr.com/finder/mcp{"mcpServers":{"com-airaptr-raptr-agent-finder":{"type":"http","url":"https://api.airaptr.com/finder/mcp"}}}Open in Cursor{"servers":{"com-airaptr-raptr-agent-finder":{"type":"http","url":"https://api.airaptr.com/finder/mcp"}}}Open in VS Code{"mcpServers":{"com-airaptr-raptr-agent-finder":{"type":"http","url":"https://api.airaptr.com/finder/mcp"}}}{"mcpServers":{"com-airaptr-raptr-agent-finder":{"serverUrl":"https://api.airaptr.com/finder/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
5| Parameter | Type | Required | Description |
|---|---|---|---|
| limit | integer | No | How many results, default 5 |
| query | string | Yes | Plain words describing the task, e.g. 'summarize sales calls' |
Details
From the project READMERaptr Agent Builder (ChatGPT app)
A ChatGPT app that turns an idea or a meeting transcript into a working single-file agent. ChatGPT's own model writes the agent; this MCP server supplies the template, checks the result, searches the public open agent registry (RAR), and explains how to run the agent in the free Brainstem.
It sits on top of the ecosystem and never changes the Brainstem: it reads the public registry and points at the public installer.
- MCP endpoint:
https://airaptr-api.azurewebsites.net/mcp(streamable HTTP, stateless, JSON responses) - Site, privacy, terms: https://airaptr.github.io/
Tools
| Tool | What it does |
|---|---|
get_agent_template | The official template and its rules |
check_agent | Checks a finished agent file against the rules |
find_agents | Searches the registry |
get_agent_code | Returns one registry agent's source |
use_agent_here | Runner so ChatGPT runs the agent in the chat on the user's data |
how_to_run_agent | Optional: keep it on your computer (Mac, Windows, Linux) |
rejection_rescue_preview | Free: explains the guideline sections an Apple App Review rejection cites |
Store: GET /store.json is the catalog for agents. Rejection Rescue: free preview at POST /rescue/preview, the full diagnosis and reply draft at POST /x402/rescue (x402, X402_PRICE_RESCUE, default $0.50, testnet by default). Tests: node --test test/*.test.mjs.
Develop
node build_template.mjs ../RAR/template_agent.py # refresh the embedded template
npx wrangler dev # local server on :8787
node test/check_real_agents.mjs ../RAR # checker vs. the template and every registry agent
test/mcp_smoke.sh http://localhost:8787 # drive the MCP endpoint
npx wrangler deploy # Cloudflare host
azure/deploy.sh # or Azure Functions
Listing copy for the ChatGPT app directory is in SUBMISSION.md.
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.