Tulip

Provides programmatic access to Tulip data and actions via MCP for LLM integration and automation.

typescript

GitHub Stars

typescript

Language

5 months ago

First Indexed

2 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": {
    "tulip-tulip-mcp": {
      "command": "npx",
      "args": [
        "@tulip/mcp-server",
        "--env",
        "/full/path/to/your/.env"
      ],
      "env": {
        "TULIP_API_KEY": "your_api_key_here",
        "TULIP_BASE_URL": "https://your-instance.tulip.co",
        "TULIP_API_SECRET": "your_api_secret_here",
        "TULIP_WORKSPACE_ID": "DEFAULT"
      }
    }
  }
}

You run a Tulip MCP Server to access Tulip’s API through a standard MCP interface. This lets you programmatically read and act on Tulip data such as tables, records, machines, stations, interfaces, users, and more from your preferred MCP client or chat-enabled workflow.

How to use

Start the server with your credentials loaded from a dedicated environment file, then connect an MCP client to your running server. You can run the server from any folder that contains your environment file, and you will point your client to it when you initialize the MCP connection.

Best practice is to create a separate environment file for each Tulip workspace you need to access, then launch the server with the corresponding --env path. This keeps credentials and tool configurations organized and reduces cross-workspace conflicts.

When you’re ready to connect, give your MCP client the appropriate command to start the server with the path to your environment file. The client will then send requests to Tulip through the MCP bridge you launched.

How to install

Prerequisites you need before starting are straightforward.

Install Node.js on your system. This is required to run the MCP server.
Create a folder for your MCP server configuration. In that folder, create a file named .env with your Tulip credentials and connection details.
Start the MCP server using the runtime command shown in the setup snippet.

Additional configuration and notes

Credential setup: In your .env file you will define these values. Replace placeholders with your actual Tulip data.

TULIP_API_KEY=your_api_key_here
TULIP_API_SECRET=your_api_secret_here
TULIP_BASE_URL=https://your-instance.tulip.co
TULIP_WORKSPACE_ID=your_workspace_id_here_if_using_account_api_key

Important: The TULIP_WORKSPACE_ID field is only required if you are using an Account API key. If you use a Workspace API key, you can leave this field empty.

Starting the server with a provided environment file: you will use the following command structure to run the MCP server and load your credentials from the specified path.

npx @tulip/mcp-server --env /full/path/to/your/.env

Tool and security considerations

You can restrict which tools are available to the MCP client by configuring the ENABLED_TOOLS variable in your .env file. This helps keep the interface focused and reduces risk by limiting capabilities to what you actually need.

Examples to tailor tool access include enabling only read-only operations or limiting to certain resource types such as tables, stations, or interfaces.

Available tools

listTables

Retrieve a list of all tables in the workspace.

getTable

Fetch details for a specific table by ID.

listStations

List all stations in the workspace.

listInterfaces

List interfaces available in the Tulip environment.

Built by

VeilStrat

AI signals for GTM teams