Squad AI
A Model Context Protocol (MCP) server that connects Squad — the AI‑powered product‑discovery and strategy platform — to any MCP‑aware large‑language‑model (LLM) application. It exposes a rich tool‑kit for creating, querying and updating product‑strategy artefacts (opportunities, solutions, outcomes, requirements, knowledge, workspaces and feedback) directly from your favourite AI co‑pilot.
This repository also contains the source code for the @squadai/tools
NPM package, which provides the client-side tools for interacting with the Squad API.
With the Squad MCP Server you can research, ideate and plan products in one conversational flow, without ever leaving your editor or chat window.
Tool prefix | Purpose | Typical actions |
---|---|---|
opportunity_* | Discover and refine product opportunities | create, list, update |
solution_* | Generate and iterate on solutions | create, list, update |
outcome_* | Track desired business or user outcomes | create, list |
requirement_* | Capture detailed requirements | create, list |
knowledge_* | Store useful references / research | create, list |
workspace_* | Manage Squad workspaces | get, update |
feedback_* | Send customer or analytics feedback into Squad | create |
Each tool conforms to the MCP JSON‑schema format so agents can introspect inputs and outputs automatically.
Pick whichever installation method suits your environment.
Download the latest binary for your operating system from the project’s GitHub releases page and run it directly:
# Windows squad-mcp.exe # macOS / Linux — make the file executable first chmod +x squad-mcp ./squad-mcp
Pass environment variables in the usual way:
SQUAD_API_KEY= SQUAD_ENV=production ./squad-mcp
# Build the image (once) docker build -t mcp/meet-squad -f Dockerfile . # Run the server on stdio docker run --rm -i \ -e SQUAD_API_KEY= \ mcp/meet-squad
git clone https://github.com/the-basilisk-ai/squad-mcp.git cd squad-mcp npm install npm run build # transpiles to ./dist node dist/index.js
This repository also includes an NPM package, @squadai/tools
, which provides a set of functions for interacting with the Squad API programmatically from your own Node.js applications or scripts.
To install the package:
npm install @squadai/tools # or yarn add @squadai/tools # or pnpm add @squadai/tools
You can then import and use the tools in your code. You will still need a Squad API key or JWT for authentication (see Quick start section above).
Example usage (Vercel AI):
import { generateText, tool } from 'ai'; import { tools as squadTools } from "@squadai/tools" const result = await generateText({ model: yourModel, tools: squadTools({ jwt: "JWT", orgId: "orgId", workspaceId: "workspaceId" }), prompt: 'What is the weather in San Francisco?', });
Add a mcpServers entry to your client’s configuration (e.g. claude_desktop_config.json or Cursor). Adjust command to match the installation method.
{ "mcpServers": { "meet-squad": { "command": "C:/path/to/squad-mcp.exe", "env": { "SQUAD_API_KEY": "YOUR_API_KEY_HERE", } } } }
{ "mcpServers": { "meet-squad": { "command": "docker", "args": [ "run", "-i", "--rm", "-e", "SQUAD_API_KEY", "mcp/meet-squad" ], "env": { "SQUAD_API_KEY": "YOUR_API_KEY_HERE", } } } }
Prefer "command": "npx"
if you installed via NPX.
Once your client restarts you should see the Squad tools (hammer 🔨 icon) listed and ready for use.
Variable | Required | Default | Description |
---|---|---|---|
SQUAD_API_KEY | Yes | – | Personal access token generated in Squad |
SQUAD_ENV | No | production | Override the Squad API base URL (staging , development , …) |
npm install npm run format npm run openapi:squad # re‑generate typed client from openapi/squad.json npm run build node dist/index.js
The test suite is work‑in‑progress; contributions welcome.
Discover shared experiences
Shared threads will appear here, showcasing real-world applications and insights from the community. Check back soon for updates!