MCP.so
ログイン

TPC Server MCP Server

@suttonwilliamd

基本情報

カテゴリ

その他

トランスポート

stdio

作者

suttonwilliamd

TPC Server MCP Server について

Thoughts Plans Changelog is an MCP compliant server for coding with AI agents

TPC Server MCP Server の設定

標準の設定はありません

このサーバーの README には解析可能な MCP 設定ブロックが含まれていません。インストール手順はリポジトリをご確認ください。

リポジトリ

TPC Server MCP Server のツール

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。

概要

What is TPC Server?

A Node.js/Express API for AI‑human collaboration, with SQLite persistence for storing thoughts and plans. It provides both a REST API and a full MCP (Model Context Protocol) server, making it ideal for AI agent workflows and developers building collaborative tools.

How to use TPC Server?

Install dependencies with npm install, then start the server via node server.js (runs on http://localhost:3001). For AI clients, run the MCP server with npm run mcp (stdio transport) and configure your MCP client accordingly. Use the REST API endpoints or the included web UI at /index.html.

Key features of TPC Server

  • Full MCP protocol implementation for AI clients (stdio transport).
  • SQLite persistence with idempotent schema migrations.
  • Modular server architecture (db/, routes/, middleware/).
  • Comprehensive testing (Jest, Playwright, MCP smoke tests).
  • Full‑text search with type/tag/limit filters.
  • Tagging system for plans and thoughts (add, edit, filter).
  • Rich text support in plan descriptions (Markdown via marked.js).

Use cases of TPC Server

  • AI agents storing and retrieving thoughts and plans via MCP.
  • Human‑in‑the‑loop editing with review flags and context aggregation.
  • Tag‑based organization and filtering of collaborative notes.
  • Rapid prototyping of AI‑assisted project management tools.
  • Searching across plans and thoughts with unified /search endpoint.

よくある質問

1

What is the MCP server and how do I use it?

The MCP server (`mcp‑server.js`) implements the Model Context Protocol over stdio transport, providing tools like list_plans, create_thought, and resources such as `tpc://plans`. Start it with `npm run mcp`.

2

What database does TPC Server use?

It uses a SQLite database stored in `data/tpc.db` for persistent storage of plans and thoughts. Schema migrations are idempotent and backward compatible.

3

How can I secure the production server?

The `/tpc.db` download endpoint is disabled by default in production. To explicitly allow it, set the environment variable `EXPOSE_TPC_DB=true`.

4

What REST endpoints are available?

Key endpoints include `GET /thoughts`, `GET /plans`, `POST /thoughts`, `POST /plans`, `PATCH /plans/:id`, `GET /search`, and tag management endpoints. Health checks are at `GET /health` and `GET /ready`.

5

How do I run tests?

Unit/integration tests: `npm test` (Jest). E2E UI tests: `npm run test:e2e` (Playwright). MCP lifecycle tests: `npm run smoke:mcp`.

コメント

「その他」の他のコンテンツ