What prerequisites are needed to use the Tecton MCP Server?
You need the `uv` package manager (install via `brew install uv`), a Tecton cluster login, and an MCP client such as Cursor (0.48+) or Claude Code.
@tecton-ai
基本情報
This MCP (Model Context Protocol) server provides tools to interact with tecton.
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"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"
}
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
Tecton MCP Server & Cursor Rules is an MCP (Model Context Protocol) server that integrates with LLM-powered editors like Cursor and Claude Code to provide tool-based context and assistance for feature engineering using the Tecton platform. It includes pre-configured rules for Cursor and Claude Code to enhance AI-assisted development of Tecton features.
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.
You need the `uv` package manager (install via `brew install uv`), a Tecton cluster login, and an MCP client such as Cursor (0.48+) or Claude Code.
Pull the latest changes from the repository (`git pull`) and restart your IDE. The MCP server is spawned as a subprocess, so no manual restart of a background service is needed.
Yes. Edit `pyproject.toml` to pin the exact version (e.g., `tecton==1.1.10`), delete `uv.lock`, re-run the smoke test to regenerate the lock file, and restart your IDE. Supported versions: Tecton ≥ 1.0.0.
By default, the server uses SDK-based tools. If a `TECTON_API_KEY` environment variable is configured, additional API-based tools (e.g., for querying Feature Services and Metrics API) are registered.
Cursor (version 0.48 and above), Claude Code, and Augment are explicitly supported with step-by-step setup guides in the README.

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

Public read-only MCP server for discovering, inspecting, installing, and sharing approved Codex-compatible animated pet packs.
OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.

Agent-Native Terminal
コメント