io.github.kody-w/raptr-agent-builder

Official8 tools

by airaptr · JavaScript

Turn an idea or meeting transcript into a working single-file AI agent, check it, use it right away.

Model Context Protocol (MCP) Server: io.github.kody-w/raptr-agent-builder

This MCP server turns an idea or meeting transcript into a working single-file AI agent. It then supports checking the result and using the generated agent immediately, based on the provided input.

🛠️ Key Features

Convert an idea or meeting transcript into a working AI agent
Produce a single-file agent
Check the agent
Use the agent right away

🚀 Use Cases

Transform meeting transcripts into executable agent code
Start from an idea and generate an immediately runnable agent
Validate and then run a newly created single-file agent

⚡ Developer Benefits

Single-file output for quick inspection
Workflow from input (idea/transcript) to checked, runnable agent

⚠️ Limitations

Scope and capabilities beyond “check it” and “use it right away” are not specified

Captured live from the server via tools/list.

get_agent_template

Use this when the user wants to build an AI agent, assistant, bot or automation from an idea, a repetitive task, a process description, or a meeting transcript (for example: automate invoices, triage support tickets, summarize meetings, follow up with leads). Returns the official single-file agent template and its rules. Fill it in yourself from what the user described, then call check_agent on the finished file before showing it to the user. Then call use_agent_here so the user can use it right away in this chat.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

check_agent

Checks a finished agent file against the template rules (manifest, naming, class, perform method, no hardcoded secrets). Call it on every agent you write, fix anything it reports, and call it again until it passes.

Parameters2

filename	string	required	File name, must end with _agent.py, e.g. invoice_triage_agent.py
code	string	required	The full Python source of the agent file

Raw schema

{
  "type": "object",
  "properties": {
    "filename": {
      "type": "string",
      "description": "File name, must end with _agent.py, e.g. invoice_triage_agent.py"
    },
    "code": {
      "type": "string",
      "description": "The full Python source of the agent file"
    }
  },
  "required": [
    "filename",
    "code"
  ],
  "additionalProperties": false
}

find_agents

Searches the open agent registry (about 1,700 single-file agents) for agents that already do what the user wants, for example when they ask 'is there an AI tool for...' or want a ready-made automation instead of building one. Use it before building from scratch, or when the user asks whether an agent exists for a task.

Parameters2

query	string	required	Plain words describing the task, e.g. 'summarize sales calls'
limit	integer	optional	How many results, default 5

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Plain words describing the task, e.g. 'summarize sales calls'"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 10,
      "description": "How many results, default 5"
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false
}

get_agent_code

Returns the full source of one agent from the registry, by its name (e.g. @bill/neuron_agent), so it can be read or adapted.

Parameters1

name

string

required

Registry name, e.g. @kody/memory_agent

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Registry name, e.g. @kody/memory_agent"
    }
  },
  "required": [
    "name"
  ],
  "additionalProperties": false
}

use_agent_here

Use this right after an agent passes check_agent, or whenever the user wants to try an agent. Returns a short Python runner so you can run the agent in this chat with your own Python tool on the user's own data (pasted text, an uploaded spreadsheet, a list). Nothing to install. If Python is unavailable, apply the agent's logic yourself by reading its code. Ask the user for their real data, run the agent, and show the result in plain words.

Parameters1

filename

string

optional

The agent file name, e.g. invoice_triage_agent.py

Raw schema

{
  "type": "object",
  "properties": {
    "filename": {
      "type": "string",
      "description": "The agent file name, e.g. invoice_triage_agent.py"
    }
  },
  "additionalProperties": false
}

how_to_run_agent

Optional, for later: how to keep an agent running on the user's own computer with the free Brainstem. Only offer this after the user has used the agent in the chat and wants to keep it.

Parameters2

os	string	optional	The user's operating system
filename	string	optional	The agent file name, if known

Raw schema

{
  "type": "object",
  "properties": {
    "os": {
      "type": "string",
      "enum": [
        "mac",
        "windows",
        "linux"
      ],
      "description": "The user's operating system"
    },
    "filename": {
      "type": "string",
      "description": "The agent file name, if known"
    }
  },
  "additionalProperties": false
}

share_agent

Use only when the user says they want to share an agent they built. Checks the agent and scans it for personal details (emails, phone numbers, secrets), then explains how to publish it to the free open agent registry under their own GitHub account. Nothing is published by this tool.

Parameters2

filename	string	required	Agent file name, ending in _agent.py
code	string	required	The full Python source of the agent

Raw schema

{
  "type": "object",
  "properties": {
    "filename": {
      "type": "string",
      "description": "Agent file name, ending in _agent.py"
    },
    "code": {
      "type": "string",
      "description": "The full Python source of the agent"
    }
  },
  "required": [
    "filename",
    "code"
  ],
  "additionalProperties": false
}

request_service

Use when the person wants something none of these tools can do and says yes to passing the request on. Records only the request text they agree to send (no name or contact). Ask before calling it.

Parameters1

request

string

required

What they want, in a sentence, as they agreed to send it

Raw schema

{
  "type": "object",
  "properties": {
    "request": {
      "type": "string",
      "description": "What they want, in a sentence, as they agreed to send it"
    }
  },
  "required": [
    "request"
  ],
  "additionalProperties": false
}

README.md2 KBView on GitHub

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

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)

Develop

bash

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.

Install

Tools (8)

get_agent_templatecheck_agentfind_agentsget_agent_codeuse_agent_herehow_to_run_agentshare_agentrequest_service

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://airaptr-api.azurewebsites.net/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "raptr-agent-builder": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://airaptr-api.azurewebsites.net/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

Model Context Protocol (MCP) Server: io.github.kody-w/raptr-agent-builder

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

get_agent_template

check_agent

find_agents

get_agent_code

use_agent_here

how_to_run_agent

share_agent

request_service

Raptr Agent Builder (ChatGPT app)

Tools

Develop

Install

Remote endpoint

Related servers