MCP Servers

mechanical-turk

An MCP server that inverts AI-human interaction: AI agents can ask humans questions via a browser console, blocking until answered.

README

mechanical-turk

A human-operator console that AI agents connect to via MCP. The inversion of a chatbot: the AI drives the conversation, the human is an on-call resource.

AI agent  ──MCP──▶  server  ──WebSocket──▶  browser console
                      ▲                            │
                      └──────── answer ────────────┘

How it works

You run the server and open the browser console
An AI agent connects to the MCP endpoint and calls ask_human
The question appears in your browser — you type an answer and hit Send
The answer is returned to the AI, unblocking it

Multiple agents can connect simultaneously. Questions queue in the inbox; the activity log tracks everything.

Setup

npm install
npm run dev

Open http://localhost:3000 for the human console.

Configure an MCP client to connect to http://localhost:3000/mcp.

MCP tools

Tool	Description
`ask_human`	Sends a question to the operator and blocks until they reply
`notify_human`	Sends a one-way message to the operator (fire and forget)

MCP client configuration

Claude Desktop / Claude Code

{
  "mcpServers": {
    "mechanical-turk": {
      "type": "http",
      "url": "http://localhost:3000/mcp"
    }
  }
}

Generic (HTTP + SSE)

POST http://localhost:3000/mcp   — initialize session / send messages
GET  http://localhost:3000/mcp   — SSE stream (mcp-session-id header required)
DELETE http://localhost:3000/mcp — close session

Scripts

Command	Description
`npm run dev`	Start with live reload (tsx watch)
`npm run build`	Compile TypeScript to `dist/`
`npm start`	Run compiled output

Environment

Variable	Default	Description
`PORT`	`3000`	Port to listen on

Recommended Servers

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official

Featured

TypeScript

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official

Featured

Local

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official

Featured

TypeScript

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official

Featured

Python

Neon Database

MCP server for interacting with Neon Management API and databases

Official

Featured

E2B

Using MCP to run code via e2b.

Official

Featured

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official

Featured

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official

Featured