How do I install one?

You can install one by adding it to your MCP client configuration (Cursor, Claude, VS Code, etc.) or by using the Stork MCP meta-server to discover and configure it automatically.

one

Noodle CLI by Noodle Seed — author, run, and deploy declarative MCP servers. Embedding the assistant in your own web app is @noodleseed/assistant.

5,955

Weekly Downloads

build.protocol_tooling.mcp#noodle-seed#mcp#model-context-protocol#agent-connectivity#headless-software#mcp-server#mcp-apps#ai-agents#typescript#cli

Visit Homepage

Back to MCP Servers

Install one in your MCP client

one 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.

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
Add one 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.
Restart your client so it picks up the new server.
Verify — ask the assistant to list available tools; one's tools should appear.

{
  "mcpServers": {
    "one": {
      "command": "npx",
      "args": [
        "-y",
        "@noodleseed/one"
      ]
    }
  }
}

Install one in Cursor

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

Install one 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). one will show up in the assistant's tool list on next launch.

Install one 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). one will show up in the assistant's tool list on next launch.

Install one in VS Code

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

npm package: @noodleseed/one

Transport

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

stdio

From the one README

# @noodleseed/one **Agent connectivity infrastructure for software teams.** Build the headless, agent-accessible version of your product for ChatGPT, Claude, Codex, embedded assistants, and any MCP-compatible client—without rebuilding your backend for every agent surface. Noodle Seed turns your existing APIs, application logic, and data into typed, governed capabilities that agents can discover and use. Author one TypeScript `server.ts`, then validate, test, deploy, and operate the resulting agent connectivity layer with the `noodle` CLI. ## What is Noodle Seed? Noodle Seed is the infrastructure layer between your software and AI agents. You keep your backend, business logic, data, and customer experience; Noodle Seed provides one governed connectivity layer across agent surfaces. In…

Other Model Context Protocol servers in the same space as one. 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.