MCP Goose Subagents Server

Provides an MCP server to delegate tasks to Goose CLI subagents, with parallel or sequential execution, recipes, and session management.

javascript

0

GitHub Stars

javascript

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "lordstyled55-goose-mcp": {
      "command": "node",
      "args": [
        "path/to/mcp-goose-subagents/src/index.js"
      ],
      "env": {
        "ALPHA_FEATURES": "true",
        "GOOSE_RECIPE_PATH": "YOUR_RECIPE_PATH"
      }
    }
  }
}

You run an MCP Goose Subagents Server to delegate development tasks to specialized Goose CLI subagents. It lets you orchestrate multiple agents in parallel or in sequence, reuse configurations via recipes, manage active sessions, and rely on Goose CLI as the sole delegation mechanism for autonomous subagents.

How to use

You can integrate this MCP server with your client by adding it to your MCP configuration. Once configured, you can delegate complex development tasks to multiple subagents, run them in parallel or one after another, and retrieve results from finished sessions.

To enable alpha Goose subagent features, ensure the Goose environment variable ALPHA_FEATURES is set to true when launching the server and during runtime.

How to install

Prerequisites you need on your system before installing will ensure a smooth run of the MCP Goose Subagents Server.

npm install
# Ensure Goose CLI and Node.js are available in your environment
# After installation, configure and run as described in the usage steps.

Configuration and running

Configure your MCP client to recognize the Goose Subagents server and enable alpha features. The server runs as a local stdio process invoked by your MCP client.

The following stdio configuration uses Node to execute the Goose subagents runner. It includes the required environment variable ALPHA_FEATURES to enable Goose subagents features.

{
  "type": "stdio",
  "name": "goose_subagents",
  "command": "node",
  "args": ["path/to/mcp-goose-subagents/src/index.js"],
  "env": {
    "ALPHA_FEATURES": "true",
    "GOOSE_RECIPE_PATH": "YOUR_RECIPE_PATH"
  }
}

Usage workflows

You can run autonomous full-stack tasks by delegating to multiple subagents in sequence or parallel. Create or reuse Goose recipes to standardize how agents perform common tasks, and track results across sessions.

Environment variables and recipes

Enable Goose alpha features by setting ALPHA_FEATURES to true. You can also specify a custom Goose recipe directory with GOOSE_RECIPE_PATH to organize reusable agent configurations.

export ALPHA_FEATURES=true
export GOOSE_RECIPE_PATH=/path/to/recipes

Available tools

delegate_to_subagents

Delegate development tasks to specialized Goose subagents with configurable roles, instructions, and execution mode (parallel or sequential).

create_goose_recipe

Create reusable Goose recipes that capture agent roles, instructions, and optional extensions and parameters.

list_active_subagents

List currently active subagent sessions and their status.

get_subagent_results

Retrieve results from completed subagent sessions using a session identifier.