Skip to content
Stork.AIstork.ai

cli

MCP server + CLI for the Unified Product Graph; drop into Claude Code or use the `upg` command.

4,590
Weekly Downloads
build.protocol_tooling.mcp#mcp#mcp-server#model-context-protocol
Visit Homepage
Back to MCP Servers

Install cli in your MCP client

cli is a Model Context Protocol server. Add it to your MCP client config once, restart, and the server's tools become available to your AI assistant. The same JSON snippet below works across all four major clients — only the config file path differs.

  1. Locate your client's MCP config file.
    • Cursor: ~/.cursor/mcp.json
    • Claude Desktop (macOS): ~/Library/Application Support/Claude/claude_desktop_config.json
    • Claude Desktop (Windows): %APPDATA%\Claude\claude_desktop_config.json
    • VS Code: Settings → Extensions → MCP
    • Windsurf: Settings → MCP Servers
  2. Add cli to the mcpServers map — paste the snippet below into your config file. If you already have other MCP servers, merge the entry into the existing mcpServers object.
  3. Restart your client so it picks up the new server.
  4. Verify — ask the assistant to list available tools; cli's tools should appear.
{
  "mcpServers": {
    "cli": {
      "command": "npx",
      "args": [
        "-y",
        "@unified-product-graph/cli"
      ]
    }
  }
}

Install cli in Cursor

Open ~/.cursor/mcp.json in your editor, paste the snippet above into mcpServers, save, and restart Cursor. cli will show up in the assistant's tool list on next launch.

Install cli in Claude Desktop (macOS)

Open ~/Library/Application Support/Claude/claude_desktop_config.json in your editor, paste the snippet above into mcpServers, save, and restart Claude Desktop (macOS). cli will show up in the assistant's tool list on next launch.

Install cli in Claude Desktop (Windows)

Open %APPDATA%\Claude\claude_desktop_config.json in your editor, paste the snippet above into mcpServers, save, and restart Claude Desktop (Windows). cli will show up in the assistant's tool list on next launch.

Install cli in VS Code

Open Settings → Extensions → MCP in your editor, paste the snippet above into mcpServers, save, and restart VS Code. cli will show up in the assistant's tool list on next launch.

npm package: @unified-product-graph/cli

Transport

cli supports the following MCP transports. Most AI clients use stdio by default for locally-installed servers.

stdio

From the cli README

# @unified-product-graph/cli The `upg` CLI — local-first governance, CRUD, and analysis for `.upg` files, plus a cursor-based "stand in the graph" command set (`use`/`here`/`at`/`ls`/`find`/`new`/`link`/`check`/`fix`). Command groups: stand-in-the-graph, setup, workspace, governance, explore, create/edit, frameworks. ``` • · • · ● · • · • Unified Product Graph ``` ## Get started in 60 seconds ```bash npm install -g @unified-product-graph/cli upg init --title "My Product" # create a .upg file in the current directory upg install-skills # install UPG skills into Claude Code # wire the MCP server (see "MCP server setup" below) # open Claude Code, then type /upg ``` Or run without installing: ```bash npx @unified-product-graph/cli health ``` ## Two su…

More build.protocol_tooling.mcp MCP servers

Other Model Context Protocol servers in the same space as cli. Each one adds different capabilities to your AI assistant — pick based on the data sources or workflows you need.

Browse the full MCP server directory or use Stork's one-line install to let your agent pick the right server automatically.