Raptr Agent Finder

io.github.kody-wv1.0.0Updated Oct 5, 2026

Find a free, ready-made AI agent for a task in the open agent registry (RAR).

VerifiedStreamable HTTPWeb executableAI & MLKnowledge & Memory

Overview

AI-generated overview

Lets an assistant search a public registry of ready-made AI agents, fetch their source, and validate agent files against a template.

What it does
The server exposes tools to search the open agent registry (RAR) for a free, ready-made agent for a task, return a specific registry agent's source code, and fetch the official agent template with its rules. It also checks a finished agent file against those rules, offers a runner so the agent can be executed in the chat on the user's data, and explains how to run an agent locally on Mac, Windows or Linux.
When to use it
Useful when you want to find an existing agent instead of writing one, or when you are building a single-file agent and want it validated against the official template before running it. It fits chat-based agent creation and reuse of published agents.
Requirements
A remote streamable HTTP endpoint; no packages, environment variables or headers are declared, and no authentication is declared. Network access to the endpoint is required.
Before you install
The runner tool executes a registry agent in the chat on the user's data, so review what an agent does before running it. Agents are fetched from a public registry and their source is third-party content; the server reads the public registry and points at a public installer rather than modifying anything.

Installation

In SourceWeft

  1. Open Raptr Agent Finder in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "raptr-agent-finder": {
      "type": "http",
      "url": "https://airaptr-api.azurewebsites.net/finder/mcp"
    }
  }
}

README

Raptr 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

ToolWhat it does
get_agent_templateThe official template and its rules
check_agentChecks a finished agent file against the rules
find_agentsSearches the registry
get_agent_codeReturns one registry agent's source
use_agent_hereRunner so ChatGPT runs the agent in the chat on the user's data
how_to_run_agentOptional: keep it on your computer (Mac, Windows, Linux)

Develop

bash
node build_template.mjs ../RAR/template_agent.py   # refresh the embedded templatenpx wrangler dev                                   # local server on :8787node test/check_real_agents.mjs ../RAR             # checker vs. the template and every registry agenttest/mcp_smoke.sh http://localhost:8787            # drive the MCP endpointnpx wrangler deploy                                # Cloudflare hostazure/deploy.sh                                    # or Azure Functions

Listing copy for the ChatGPT app directory is in SUBMISSION.md.

Source: README.md at commit ec1544c

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v1.0.0LatestOct 5, 2026