About goose_mcp
goose_mcp is an experimental collection of MCP servers intended for Goose, following its custom extensions guide. Each server can be set up in its own Python virtual environment and added through `goose configure`.
Key features
- 01Multiple MCP server directories
- 02Per-server Python virtual environments
- 03Goose configuration via command
Use cases
- 01Set up an MCP server for Goose
- 02Add a locally configured server to Goose
MCP support
It provides MCP servers for use with Goose, which can be registered with `goose configure` using each server's run command.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEgoose_mcp
An attempt at MCP servers for Goose
I tried to follow their custom-extensions guide
Running uv sync in each directory creates the Python .venv environment for each mcp.
From there you can add the uv run /foo/bar/path/to/mcp_server/.venv/bin/mcp_server_name command to your goose configure and it should show up in your goose.
The only thing not afraid of Canada Mooses, is Canada Gooses.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.