mcpField
R
rapp-agent-builder

rapp-agent-builder

Remote
kody-w.github.ioAI & Agents0Updated 3w ago

About rapp-agent-builder

rapp-agent-builder is a ChatGPT app for turning ideas or meeting transcripts into single-file RAPP agents. It provides an official template, validates agent files, and can run agents in chat.

Key features

  1. 01Generate single-file RAPP agents
  2. 02Provide the official agent template
  3. 03Check agent files against rules
  4. 04Search the public agent registry
  5. 05Run agents on chat data

Use cases

  1. 01Draft an agent from a project idea
  2. 02Create an agent from meeting notes
  3. 03Validate an agent before use
  4. 04Find and run a registry agent

MCP support

The MCP server provides tools for templates, validation, registry search and source retrieval, in-chat execution, and run instructions.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://rapp-agent-builder.azurewebsites.net/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

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

8

This tool takes no parameters.

Details

From the project README

RAPP Agent Builder (ChatGPT app)

A ChatGPT app that turns an idea or a meeting transcript into a working single-file RAPP agent. ChatGPT's own model writes the agent; this MCP server supplies the template, checks the result, searches the public RAPP Agent Registry, and explains how to run the agent in the free RAPP Brainstem.

It sits on top of the ecosystem and never changes the Brainstem: it reads the public registry and points at the public installer.

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

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

Markdown supported

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.