MCP.so
Sign In

TPC Server MCP Server

@suttonwilliamd

Basic information

Category

Other

Transports

stdio

Author

suttonwilliamd

About TPC Server MCP Server

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

TPC Server MCP Server config

No standard config provided

This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.

Repository

TPC Server MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

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.

Frequently asked questions

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`.

Comments

More Other MCP servers