Raptr Agent Builder

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

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

VerifiedStreamable HTTPWeb executableAI & ML Developer Tools

Overview

AI-generated overview

Turns an idea or meeting transcript into a working single-file AI agent, checks it against rules, and runs it in chat.

What it does: This remote MCP server supplies an official agent template and its rules, checks a finished agent file against those rules, and searches a public open agent registry. It can return one registry agent's source code and provides a runner so the assistant executes the agent in the chat on the user's own data. It also explains how to keep and run the agent locally on Mac, Windows, or Linux.
When to use it: Use it when you want to go from a rough idea or a meeting transcript to a runnable single-file agent without writing the scaffolding yourself. It fits quick prototyping, checking an agent you already drafted, and finding existing agents in the public registry to reuse.
Requirements: A remote streamable HTTP endpoint; no package, environment variable, or header is declared, and no authentication is declared. The assistant connects to the hosted endpoint, so network access is needed.

Before you install

The runner executes a generated agent in the chat on the user's data, so review what the agent does before feeding it sensitive content. Generated code and registry agent source come from third parties and should be inspected before local use. The server reads a public registry and points at a public installer; no credentials are requested.

Installation

In SourceWeft

Open Raptr Agent Builder in the dashboard and add it to a workspace.
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-builder": {
      "type": "http",
      "url": "https://airaptr-api.azurewebsites.net/mcp"
    }
  }
}

README