Tecton MCP Server & Cursor Rules

by tecton-ai

3 stars
171 downloads
Not rated
GitHub

About

This MCP (Model Context Protocol) server provides tools to interact with tecton.

Details

Author
tecton-ai
GitHub stars
3
Downloads
171
Categories
Developer Tools

- Query code examples index using vector database
- Retrieve Tecton documentation snippets based on queries
- Fetch complete or specific Tecton SDK reference information
- Query Tecton Metrics API for system metrics
- API-based tools for Tecton Feature Services (when API key configured)
- Supports Cursor, Claude Code, and Augment integrations

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Tecton MCP Server & Cursor Rules
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Clone the repository, install the uv package manager, authenticate with your Tecton cluster, then configure your MCP client (Cursor, Claude Code, or Augment) to add the MCP server using the provided JSON configuration. Symlink the .cursor/rules or CLAUDE.md files into your feature repository. After restarting the IDE, you can start using Tecton's Co-Pilot for feature engineering.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "tecton mcp server & cursor rules": {
            "tecton-mcp": {
                "command": "uv",
                "args": [
                    "--directory",
                    "<path-to-local-clone>",
                    "run",
                    "mcp",
                    "run",
                    "src/tecton_mcp/mcp_server/server.py"
                ],
                "env": {
                    "MCP_SMOKE_TEST": "1"
                }
            }
        }
    }
}

McpServers

{
    "tecton-mcp": {
        "command": "uv",
        "args": [
            "--directory",
            "<path-to-local-clone>",
            "run",
            "mcp",
            "run",
            "src/tecton_mcp/mcp_server/server.py"
        ],
        "env": {
            "MCP_SMOKE_TEST": "1"
        }
    }
}

Tecton MCP Server & Cursor Rules

Tecton's Co-Pilot consists of an MCP Server rules for MCP clients such as Cursor and Claude Code.
Read this blog to learn much more.

> ℹ️ Info: This guide will walk you through setting up the Tecton MCP server with this repository and configuring your feature repository to use it while developing features with Tecton.

Table of Contents

- Tecton MCP Tools
- Quick Start
- Setup Tecton with Cursor
- Setup Tecton with Claude Code
- Setup Tecton with Augment
- Architecture
- How to Update the Tecton MCP Server
- How to Use Specific Tecton SDK Version
- Troubleshooting
- Resources

Tecton MCP Tools

The Tecton MCP server exposes the following tools that can be used by an MCP client such as Cursor or Claude Code:

| Tool Name | Description |
| --------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------- |
| query_example_code_snippet_index_tool | Finds relevant Tecton code examples using a vector database. Helpful for finding usage patterns before writing new Tecton code. |
| query_documentation_index_tool | Retrieves Tecton documentation snippets based on a query. Provides context directly from Tecton's official documentation. |
| get_full_tecton_sdk_reference_tool | Fetches the complete Tecton SDK reference, including all available classes and functions. Use when a broad overview of the SDK is needed. |
| query_tecton_sdk_reference_tool | Fetches the Tecton SDK reference for a specified list of classes or functions. Ideal for targeted information on specific SDK components. |
| query_tecton_metrics_tool | Queries the Tecton Metrics API. Returns point-in-time system metrics in human-readable or raw OpenMetrics format. |

> ℹ️ API-based Tools: If the MCP server is configured with a TECTON_API_KEY environment variable, the MCP server will register additional API-based tools including Tecton Feature Services and the Metrics API tool. This makes it possible for agents to query online feature services for fresh features from batch, streaming and real-time data sources and access system metrics.

Prerequisites

1. Install the uv package manager:

   brew install uv
   

Quick Start

1. Clone this repository to your local machine:

   git clone https://github.com/tecton-ai/tecton-mcp.git
   cd tecton-mcp
   pwd
   

Note: The directory where you just cloned the repository will be referred to as <path-to-local-clone> in the following steps.

2. Verify your installation by running the following command.

   MCP_SMOKE_TEST=1 uv --directory <path-to-local-clone> run mcp run src/tecton_mcp/mcp_server/server.py
   

The command should exit without any errors and print a message similar to MCP_SMOKE_TEST is set. Exiting after initialization.. This confirms that your local setup works correctly—Cursor will automatically spawn the MCP server as a subprocess when needed.

3. Log into your Tecton cluster to authenticate the Tecton SDK used by the Tecton MCP server:

   tecton login yourcluster.tecton.ai
   

4. Configure Cursor (or any other MCP client) with the MCP server (see below)
- Setup Tecton MCP with Cursor
- Setup Tecton MCP with Claude Code

5. Start AI-Assisted Feature Engineering :-)

Now you can go to your Feature Repository in Cursor and start using Tecton's Co-Pilot - directly integrated in Cursor.

View this Loom to see how you can use the integration to build new features: https://www.loom.com/share/3658f665668a41d2b0ea2355b433c616

Setup Tecton MCP with Cursor

The following is tested with Cursor 0.48 and above

Configure the Tecton MCP Server in Cursor

Navigate to Cursor Settings -> MCP Tools and click the "Add a Custome MCP Server" button, which will open Cursor's mcp.json file.
Add the following configuration to this file. Make sure you modify the path <path-to-local-clone> to match the directory where you cloned the repository:

{
    "mcpServers": {
        "tecton": {
            "command": "uv",
            "args": [
                "--directory",
                "<path-to-local-clone>",
                "run",
                "mcp",
                "run",
                "src/tecton_mcp/mcp_server/server.py"
            ]
        }
    }
}

Add Tecton-specific Cursor rules

Symlink the cursorrules from this repository's .
cursor/rules
folder
into your feature repository. Using symlinks ensures that any updates to the original rules will automatically be picked up in your feature repository:

```bash

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.