The MCP Server Directory
Every Model Context Protocol server, scored on reliability, documentation, maintenance, and adoption. Independent, opinionated, refreshed daily from the official registry.
What this is
The MCP Server Directory is a live, independently maintained index of Model Context Protocol servers published to the official registry. Each server is scored 0–10 on four dimensions: reliability, documentation quality, maintenance velocity, and adoption. The directory is free, updated daily, and built by MegaOne AI.
Gmail
4.1/10Gmail MCP server — send, read, and search email. By Strider Labs.
Instacart
4.1/10Instacart grocery ordering - search products, manage cart, place orders.
Kroger
4.1/10MCP server for Kroger - search products, manage cart, place grocery orders
Southwest
4.1/10MCP server for Southwest Airlines - search flights, manage bookings
Target
4.1/10MCP server for Target - search products, manage cart, track orders
Walmart
4.1/10MCP server for Walmart - search products, manage cart, track orders
Yelp
4.1/10MCP server for Yelp - search businesses, read reviews, make reservations
Openapi Navigator
4.1/10Navigate and query OpenAPI specs with fuzzy search, pagination, and API testing
Google Gsc
4.1/10Google Search Console MCP: search analytics, URL inspection, site management.
Hot Memory MCP
4.1/10Two-tier memory: hot cache (0ms) + semantic search. Self-organizing.
MCP Icon Visual
4.1/10Search, retrieve, compare, and render SVG icons visually for AI agents.
Dida MCP Server
4.1/10Hotel search, booking, and review MCP server with 12+ detailed fields per hotel
Pubcrawl
4.1/10PubMed literature search and US/UK drug labelling for AI assistants.
Github Gist
4.1/10MCP server to create, read, update, list, and search GitHub Gists from your IDE
Markdown
4.1/10Markdown MCP — search, extract sections, list headings, find code blocks.
Npm Plus
4.1/10npm MCP — search packages, bundle sizes, vulnerabilities, compare downloads.
Npm Search
4.1/10npm search MCP — find packages, view details, compare, check downloads.
Gitlab Docs
4.1/10GitLab documentation search for AI assistants via Model Context Protocol (MCP)
MCP Gsc
4.1/10Google Search Console MCP server — query performance, sitemaps, indexing & more
MCP Docs Server
4.1/10MCP server for searching MCP protocol documentation
Zoekt MCP
4.1/10Fast indexed code search for AI agents, powered by Sourcegraph Zoekt.
Axon Research
4.1/10AI agent ecosystem research, DeFi analysis, and market research tools
Ref Tools MCP
4.1/10Token efficient search for coding agents over public and private documentation.
Smart Web
4.1/10Web search, direct-URL fetch, crawl, and docs export MCP. smartfetch for URLs.
Npm
4.1/10npm package search, audit, bundle analysis for AI agents
Web
4.1/10Web scraping, search, monitoring, and HTML-to-markdown for AI agents
Notion MCP
4.1/10Notion MCP server — search, export, and import pages as markdown
MCP Omnisearch
4.1/10MCP server for integrating Omnisearch with LLMs
Synapbus
4.1/10MCP-native agent-to-agent messaging hub with channels, DMs, and semantic search
Tavily MCP
4.1/10MCP server for advanced web search using Tavily
Superjob MCP
4.1/10MCP server for SuperJob.ru API — vacancy search, employers. Requires API key.
Vk MCP
4.1/10MCP server for VK API — wall posts, news search, users, groups. 4 tools.
Mnemograph
4.1/10Event-sourced knowledge graph memory for AI coding agents with semantic search
Cozo Memory
4.1/10Local-first memory system for AI agents with hybrid search and graph reasoning
Code Index MCP
4.1/10Fast local source code searching using Zoekt trigram-based indexing
Claudeink
4.1/10Save, search, and compile valuable knowledge from your Claude conversations.
Ticket Discovery
4.1/10Search and compare concert ticket prices across platforms
MCP Webgate
4.1/10Web search that doesn't wreck your AI's memory.
MCP Webgate
4.1/10Web search that doesn't wreck your AI's memory.
X402Search MCP
4.1/10Search 13,000+ x402-enabled APIs from your AI agent. Powered by x402search.xyz
Kalshi
4.1/10Search, analyze, and trade Kalshi prediction markets through Claude Desktop
Mote Registry
4.1/10Search the MOTE AI agent registry for machine-readable businesses.
Local Commerce
3.9/10Search 7,000+ local service businesses across America by category, location, or keyword.
Ens Tools
3.9/1034 MCP tools to search, register, manage, value, and trade ENS names. AI-powered intelligence layer.
MCP Server
3.9/10Search and verify 360K+ business entities with trust scores and W3C credentials.
Seltz Ai Seltz MCP
3.9/10Provides AI assistants with access to Seltz's powerful Web Search capabilities.
Kaszek Kaszek Attio MCP
3.9/10Automate Attio CRM workflows with fast search and bulk operations across companies, people, deals,…
Clintrials MCP
3.9/10Provide structured access to ClinicalTrials.gov data for searching, retrieving, and analyzing clin…
Free · No spam
New servers, score changes, breakages
Every Monday: what shipped, what broke, what's worth trying. Five minutes. No filler.
Four dimensions, weighted
- Reliability (30%) — repository present, permissive license, not archived, official status.
- Documentation (20%) — description length, website presence, README quality.
- Maintenance (25%) — how recently the code was pushed; versioning discipline.
- Adoption (25%) — GitHub stars (log-scaled), remote availability, official endorsement.
What is MCP?
MCP stands for Model Context Protocol. It is an open standard introduced by Anthropic in late 2024 that lets AI assistants like Claude connect to external tools, data sources, and services through a common interface. An MCP server is a small program that exposes one capability (file access, a database, an API) to any MCP-compatible AI client.
Where does the data come from?
Every server in this directory is pulled from the official Model Context Protocol Registry at registry.modelcontextprotocol.io. We also enrich each entry with GitHub metadata (stars, last commit, license, primary language) where a repository is linked. The full re-scan runs daily.
How are servers scored?
Each server gets a 0–10 overall score, weighted from four sub-scores: reliability (30%), documentation (20%), maintenance (25%), and adoption (25%). The full methodology is visible on this page under "How scoring works".
Is this affiliated with Anthropic?
No. MegaOne AI is independent. Anthropic created the MCP standard and maintains the reference implementations, but this directory is built separately and rates all servers including Anthropic's own.
How often does the directory update?
The pipeline re-fetches the full registry and re-scores every active server once per day. Individual entries are refreshed whenever a new version is published to the official registry.
Is it free?
Yes. Browsing, filtering, and searching the directory is free. The weekly email briefing is free. There is no account required.