Tecton MCP Server

Official

hybrid server

The server is able to function both locally and remotely, depending on the configuration or use case.

Integrations

  • Utilizes Python as the runtime environment with specific version requirements (>=3.10)

Tecton MCP Server

This is a Mission Control Protocol (MCP) server from Anthropic for Tecton that provides a set of tools to interact with Tecton clusters, manage feature stores, and execute Tecton CLI commands.

Features

The server provides the following MCP tools:

CLI Tools

  • tecton_cli_help: Get structured help information about available Tecton CLI commands
  • tecton_cli_execute: Execute Tecton CLI commands

Feature Store Management

  • list_workspaces: List all workspaces in the connected Tecton cluster
  • list_feature_views: List all feature views with their metadata
  • list_feature_services: List all feature services with their metadata
  • list_transformations: List all transformations with their metadata
  • list_data_sources: List all data sources with their metadata
  • list_entities: List all entities with their metadata

Configuration Tools

  • get_feature_service_configuration: Get detailed configuration of a feature service
  • get_feature_view_configuration: Get detailed configuration of a feature view
  • get_feature_view_code: Get the Python code definition of a feature view

Setup

Prerequisites

  • Python >=3.10 or compatible version
  • Tecton SDK installed and configured
  • Mission Control Protocol (MCP) installed

Installation

  1. Install required Python packages:
pip install httpx click cloudpickle
  1. Install Tecton SDK:
pip install tecton
  1. Install MCP:
pip install mcp

Configuration

Add the following to your MCP server configuration:

{ "mcpServers": { "tecton": { "command": "/path/to/python", "args": [ "--directory", "/path/to/tecton", "run", "tecton.py" ], "env": { "PYENV_VERSION": "3.9.11" } } } }

Replace /path/to/python and /path/to/tecton with your actual paths.

Usage

Starting the Server

  1. First, ensure you have Tecton configured and logged in:
tecton login
  1. Then run the server using:
python tecton.py

The server will start and listen for MCP commands.

Using the Tools

All tools are available through the MCP interface. Here are some example uses:

  1. List all workspaces:
workspaces = await list_workspaces()
  1. Get feature view configuration:
config = await get_feature_view_configuration(name="my_feature_view", workspace="my_workspace")
  1. Execute a Tecton CLI command:
result = await tecton_cli_execute(command="workspace list")

Error Handling

The server includes comprehensive error handling:

  • All tools return empty lists or empty strings on failure
  • Errors are logged using the _err function
  • General operations are logged using the _log function

Dependencies

  • Core Python:
    • typing (built-in)
    • httpx
    • click
    • cloudpickle
  • Tecton:
    • tecton
    • tecton._internals
    • tecton.cli.cli
    • tecton_core
    • tecton_proto
  • MCP:
    • mcp.server.fastmcp
  • Local:
    • utils (containing _err, _log, and run_command)

Contributing

Feel free to submit issues and enhancement requests!

-
security - not tested
F
license - not found
-
quality - not tested

Provides a set of tools to interact with Tecton clusters, manage feature stores, and execute Tecton CLI commands through the Mission Control Protocol.

  1. Features
    1. CLI Tools
      1. Feature Store Management
        1. Configuration Tools
        2. Setup
          1. Prerequisites
            1. Installation
              1. Configuration
              2. Usage
                1. Starting the Server
                  1. Using the Tools
                  2. Error Handling
                    1. Dependencies
                      1. Contributing