GooseTeam

Look, a flock of geese! An MCP server and protocol for Goose agent collaboration.

Catalog onlyCatalog onlySTDIO

Overview

GooseTeam is a collaborative platform designed for Goose agents to work together using a Model Context Protocol (MCP) server, enabling efficient task management and communication among agents.

To use GooseTeam, install the Goose CLI, configure the extension, and run the necessary npm scripts to set up the server and launch agents for task management.

Natural Language and Mermaid Markdown protocols for agent instructions. - Agent registration and unique ID assignment. - Message and task management capabilities. - Remote server connectivity for multiple agents.

Coordinating tasks among multiple AI agents.
Managing agent communication and message storage.
Implementing collaborative workflows in AI-driven projects.

Add to your AI client

Use these steps to connect GooseTeam in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "gooseteam-cliffhall": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-gooseteam-cliffhall"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "gooseteam-cliffhall": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-gooseteam-cliffhall"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "gooseteam-cliffhall": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-gooseteam-cliffhall"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "gooseteam-cliffhall": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-gooseteam-cliffhall"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "gooseteam-cliffhall": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-gooseteam-cliffhall"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "gooseteam-cliffhall": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-gooseteam-cliffhall"
      ]
    }
  }
}

FAQ

Can GooseTeam support multiple agents?

Yes! GooseTeam is designed to facilitate collaboration among multiple agents.

Is there a specific setup required to run GooseTeam?

Yes! You need to install the Goose CLI and follow the setup instructions provided in the documentation.

What programming language is GooseTeam built with?

GooseTeam is built using TypeScript.

Developer tools