What prerequisites are needed?
Python 3.11+ and a running instance of the repair_world_application are required.
@nikhilpurwant
Basic information
Using Google ADK with and MCP server written for the repair_world_application
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"google-adk-mcp": {
"command": "python",
"args": [
"-m",
"venv",
".venv"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
google-adk-mcp is a sample project demonstrating how to build a Google ADK (Agent Developer Kit) agent that connects to an external MCP server. The MCP server exposes tools for interacting with the repair_world_application, such as creating and viewing repair requests.
Clone the repository, create a Python virtual environment (Python 3.11+), and install dependencies. Ensure the repair_world_application is running. Then launch the agent either via adk web for a web UI at http://localhost:8000 or by running python agent-repairworld.py for a console interface.
Python 3.11+ and a running instance of the repair_world_application are required.
You can run the agent in web mode with `adk web` (access UI at localhost:8000) or in console mode with `python agent-repairworld.py`.
The MCP server is the external package `mcp-server-repairworld` available on PyPI, installed via the project’s requirements.
Free moving quotes for AI agents from Next Generation Movers, a licensed interstate mover (USDOT 3764697). US long-distance nationwide and local DC/MD/VA. Indicative ballpark price and booking options; optional $0.01 x40

Model Context Protocol Servers
🚀 The fast, Pythonic way to build MCP servers and clients.

Model Context Protocol Servers
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
Comments