tooldirectory-mcp

tooldirectory-mcp

Search the AI Tool Directory catalog of 2,000+ AI tools — compare tools, find curated alternatives, and check whether a tool is still active, defunct, or acquired (backed by the AI Graveyard dataset).

Category
Visit Server

README

Tool Directory MCP Server

npm version license

MCP server for the AI Tool Directory — a live, human-edited catalog of 2,000+ AI tools. Lets any MCP client (Claude Desktop, Claude Code, Cursor, Windsurf, agent frameworks) query the catalog mid-task instead of guessing from a frozen training cut.

The headline tool is check_tool_status: whether an AI tool is still alive. It's the one fact LLMs reliably get wrong — models keep recommending products that shut down months ago. This server answers it from the directory's AI Graveyard, a maintained dataset of 150+ defunct and acquired AI tools, and suggests live alternatives when a tool is dead.

Tools

Tool What it does
search_tools Hybrid semantic search across the catalog — by keyword, use case, or category.
get_tool Full profile of one tool: pricing, features, editorial verdict, last human-verified date.
check_tool_status Is this tool active, deceased, or acquired? Date + cause if it shut down, plus live alternatives.
find_alternatives Curated alternatives to a tool; live replacements if it's defunct.
compare_tools Side-by-side comparison of two tools, with the editor's head-to-head verdict when one exists.
list_tools Top-rated active tools for a category or job role, optionally filtered by pricing.

Read-only, no API key, no signup.

Install

Hosted endpoint (no install)

The server is also available as a remote MCP (Streamable HTTP) — point your client at:

https://tooldirectory.ai/api/mcp

Claude Desktop / Claude Code

{
  "mcpServers": {
    "tooldirectory": {
      "command": "npx",
      "args": ["-y", "tooldirectory-mcp"]
    }
  }
}

Or with Claude Code:

claude mcp add tooldirectory -- npx -y tooldirectory-mcp

Cursor / Windsurf / other MCP clients

Use the same stdio command: npx -y tooldirectory-mcp.

Docker

docker build -t tooldirectory-mcp .
docker run -i tooldirectory-mcp

Example prompts

  • "Is Jasper still operating? What happened to Inflection Pi?"
  • "Find me alternatives to Midjourney with a free tier."
  • "Compare Gamma and Beautiful.ai for making decks."
  • "What are the best AI tools for sales teams?"

How it works

This package is a thin stdio front-end over the canonical hosted endpoint at tooldirectory.ai/api/mcp, where the search (Meilisearch hybrid semantic) and catalog logic live. Tool schemas are declared locally, so initialize and tools/list respond instantly with no network call; tools/call proxies to the hosted endpoint. Zero runtime dependencies.

Set TOOLDIRECTORY_MCP_ENDPOINT to override the upstream endpoint (e.g. for testing).

About the data

The catalog is maintained by Tool Directory — an AI tool company run by humans that use AI. Every listed tool has a lifecycle status; editorial reviews carry a named editor and a last-verified date. Related machine-readable surfaces:

License

MIT

Recommended Servers

playwright-mcp

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)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

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

Official
Featured
Local
graphlit-mcp-server

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

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

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Exa Search

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

Qdrant Server

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

Official
Featured