Raptr Agent Builder

com.airaptrPublished by airaptr.comOfficial publisherv1.3.0Updated Oct 24, 2026

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

The publisher's own server: Dogg World Check

VerifiedStreamable HTTPWeb executableKnowledge & MemoryDeveloper ToolsAI & ML

Overview

AI-generated overview

A remote MCP server that helps an assistant turn an idea or transcript into a single-file AI agent, check it, try it, and find existing agents in a public open.

What you can do
Get the official single-file agent template and its rules, and check a finished agent file against them until it passes. Search the open agent registry and read the full source of a listed agent. Get a short Python runner to try an agent in the chat on the user's own data, and learn how to keep it running locally. Prepare an agent for sharing by scanning it for personal details, and explain guideline sections cited in an Apple App Review rejection. Record a service request the user agrees to send.
When to use it
Useful when someone wants to build an AI agent, bot or automation from an idea, repetitive task or meeting transcript, or wants to check whether a ready-made agent already exists. Also handy for understanding which App Review guidelines a rejection cites.
Requirements
A remote streamable HTTP endpoint; no local install, packages, environment variables or headers are declared. The in-chat runner needs Python available to the assistant; keeping an agent on the user's own computer uses the free Brainstem.
Before you install
The full Rejection Rescue diagnosis is a paid x402 endpoint with a default price, testnet by default. Sharing an agent explains publishing to a public registry under the user's GitHub account, though the tool itself publishes nothing. request_service sends the request text the user agrees to, with no name or contact. Registry agent source is third-party code to review before running.

Installation

In SourceWeft

  1. Open Raptr Agent Builder 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.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.airaptr%2Fraptr-agent-builder/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "raptr-agent-builder": {
      "type": "http",
      "url": "https://api.airaptr.com/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)
rejection_rescue_previewFree: 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

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 f110430

Tools

9

get_agent_template

Get the 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.

Takes no parameters.

check_agent

Check an agent file

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.

Parameterscoderequiredfilenamerequired

find_agents

Find existing 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.

Parameterslimitqueryrequired

get_agent_code

Get an agent's 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.

Parametersnamerequired

use_agent_here

Use the agent in this chat

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.

Parametersfilename

how_to_run_agent

Keep an agent running on your computer

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.

Parametersosfilename

share_agent

Share an agent with everyone

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.

Parameterscoderequiredfilenamerequired

rejection_rescue_preview

Explain an App Store rejection

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.

Parameterstextrequired

request_service

Ask us to build something

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.

Parametersrequestrequired

Version history

1
  1. v1.3.0LatestOct 16, 2026

Score

90% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.

Other Airaptr integrations

Dogg World Check

com.airaptrOfficial publisher

Remote MCP server that returns current world data snapshots with public tick numbers and SHA-256 fingerprints, plus text fingerprinting and a request channel.

Streamable HTTPWeb executable
Finance3 toolsOct 24, 2026

Raptr Names

com.airaptrOfficial publisher

Checks whether domain names and GitHub names are free, with prices, to help an assistant brainstorm and validate names for a business or project.

Streamable HTTPWeb executable
Web Search & Scraping4 toolsOct 28, 2026

Raptr Domains

com.airaptrOfficial publisher

Remote MCP server for checking availability and price of up to 20 domain names at once and explaining how to register them.

Streamable HTTPWeb executable
Web Search & Scraping3 toolsOct 24, 2026

Raptr Agent Finder

com.airaptrOfficial publisher

A remote MCP server that lets an assistant search a public registry of ready-made single-file AI agents, read their source, and run one in the chat.

Streamable HTTPWeb executable
Developer Tools5 toolsOct 24, 2026