AI Workbench MCP

A tiny, read-only MCP server for reusable AI prompts and assistant blueprints.

AI Workbench MCP exposes a small local catalog over Model Context Protocol stdio. It is intentionally boring in the best way: no network calls, no shell execution, no account access, no file writes, no hidden provider request.

It gives an MCP host three tools:

Why this exists

A lot of AI repos jump straight from "here is a prompt" to "this is an agent." I wanted a smaller boundary that is easy to inspect.

The server keeps the useful parts local and makes its limits obvious:

• read-only tool contracts;
• explicit MCP trust hints;
• bounded input sizes;
• strict top-level schemas;
• no runtime dependencies outside the Python standard library;
• real stdio handshake tests;
• named tests for every public tool.

Quick start

1. Create a virtual environment

python -m venv .venv

Activate it, then install the package:

python -m pip install -e .

2. Run the smoke client

python examples/smoke_client.py

A successful run prints the negotiated MCP version and all three tool names.

3. Point an MCP host at the server

Launch command:

alptugharun-ai-workbench-mcp

This repository documents the stdio server itself. Host-specific configuration changes over time, so use the current documentation for the MCP client you are connecting.

Security model

Every public tool declares:

{
  "readOnlyHint": true,
  "destructiveHint": false,
  "idempotentHint": true,
  "openWorldHint": false
}

The implementation does not import HTTP clients, subprocess modules, filesystem-write helpers, browser libraries, or provider SDKs.

That does not mean "trust any MCP server." It means this repository keeps its own boundary narrow and testable.

Verify it yourself

python -m unittest discover -s tests -v
python examples/smoke_client.py

CI runs the package and protocol tests on Linux and Windows.

Package / registry status

The first package candidate is 0.1.0a1.

PyPI and official MCP Registry publication are intentionally treated as separate proof steps. This README will not claim either one until the exact published artifact can be installed from a clean environment and called from a real MCP host.

See REGISTRY-PUBLISHING.md.

Contributing

Small, reproducible improvements are welcome. The most useful contributions right now are:

• real MCP host verification;
• protocol edge-case tests;
• clearer failure messages;
• documentation corrections;
• narrowly scoped catalog improvements.

Please read CONTRIBUTING.md before opening a PR.

Origin

This project was extracted from AI Social Media Toolkit so the MCP server can evolve as a focused product instead of being buried inside a larger creator/AI repository.

Built by Alptuğ Harun.

License

MIT — see LICENSE.