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

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

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

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "raptr-agent-builder": {
      "url": "https://airaptr-api.azurewebsites.net/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (9)

• get_agent_template read-only

  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.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• check_agent read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• find_agents read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent not declared · open-world yes

• get_agent_code read-only

  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.

  Parameters:

  • name (required) — string — Registry name, e.g. @kody/memory_agent

  Hints: read-only yes · destructive no · idempotent not declared · open-world yes

• use_agent_here read-only

  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.

  Parameters:

  • filename — string — The agent file name, e.g. invoice_triage_agent.py

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• how_to_run_agent read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• share_agent read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• rejection_rescue_preview read-only

  Use when the user pastes a rejection message from Apple App Review (it cites guidelines such as "Guideline 5.1.1(i)"). Free. Returns each cited guideline section it recognizes, with its title and what Apple means by it, and lists sections it does not know. The full version (likely causes, a fix list and a reply draft to App Review) is a separate paid HTTP call; the result says its price and route.

  Parameters:

  • text (required) — string — Apple's rejection message, as received (up to 20 KB)

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• 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.

  Parameters:

  • request (required) — string — What they want, in a sentence, as they agreed to send it

  Hints: read-only no · destructive no · idempotent not declared · open-world no

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.