AI Workbench MCP

io.github.alptugharunv0.1.0a1Updated Oct 3, 2026

Read-only MCP server for reusable AI prompts and assistant blueprints.

VerifiedSTDIODesktop onlyAI & MLKnowledge & Memory

Overview

AI-generated overview

A read-only local MCP server that lists, renders, and returns bundled AI prompt templates and assistant blueprints.

What it does
It exposes three read-only tools over stdio: list_prompts lists the bundled prompt templates and assistant blueprints, render_prompt fills a bundled template with explicit string variables, and get_assistant returns one assistant blueprint for ChatGPT, Claude, Gemini, Grok, or a portable Agent Skill format. The catalog is local and bundled; the server makes no network calls, runs no shell commands, and writes no files.
When to use it
Worth adding when you want an assistant to pull reusable prompts or assistant blueprints from a small, inspectable local catalog instead of pasting them by hand. It suits users who prefer a narrow, read-only tool surface with no accounts or external services.
Requirements
A local Python runtime; the package is published on PyPI as alptugharun-ai-workbench-mcp and can be run with uvx or installed with pip. It needs a stdio-capable MCP host, and the README notes it was exercised with Cursor while other clients may differ. No accounts, API keys, environment variables, or headers are declared.
Before you install
The server is described as read-only with no network calls, shell execution, account access, or file writes, and its tools declare read-only, non-destructive, idempotent, and closed-world hints. The published version is an alpha, and the README states host verification is maintainer-run evidence rather than independent endorsement or a universal compatibility claim.

Installation

In SourceWeft

  1. Open AI Workbench MCP in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

AI Workbench MCP

[CI] [CodeQL] [OpenSSF Scorecard]

[English] [Türkçe]

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

[MCP read-only] [Python 3.10+] [Dependency-free runtime] [MIT]

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:

ToolResult
list_promptsLists the bundled prompt templates and assistant blueprints
render_promptFills a bundled prompt template with explicit string variables
get_assistantReturns one assistant blueprint for ChatGPT, Claude, Gemini, Grok, or portable Agent Skill format

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

Install the published alpha package:

bash
python -m pip install "alptugharun-ai-workbench-mcp==0.1.0a1"

Then point a stdio-capable MCP host at the server:

Launch command:

text
alptugharun-ai-workbench-mcp

This repository documents the stdio server itself. For the host we have actually exercised, use the copy/paste Cursor setup and 3-tool verification guide. Other MCP clients can differ, so use their current documentation rather than assuming Cursor's configuration is portable.

Security model

Every public tool declares:

json
{  "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

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

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

Package / registry status

PyPI: alptugharun-ai-workbench-mcp==0.1.0a1 is published through GitHub OIDC Trusted Publishing. The release workflow also signs the wheel with keyless Sigstore.

A clean Windows virtual environment installed the exact PyPI version successfully, negotiated MCP protocol 2025-06-18, listed all three tools, completed successful render_prompt and get_assistant calls, and returned a bounded error for an unknown tool.

Official MCP Registry: io.github.alptugharun/ai-workbench-mcp is published and currently reports active in the production registry.

Real-host verification: a maintainer-run Cursor 3.20.21 session invoked list_prompts, render_prompt and get_assistant successfully against the published package. This is host evidence, not an independent third-party endorsement or a universal compatibility claim.

See REGISTRY-PUBLISHING.md and HOST-VERIFICATION.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.

Source: README.md at commit 4f97463

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v0.1.0a1LatestOct 3, 2026