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.
Zsh Tool
4.1/10Zsh for Claude Code. PTY mode lets Claude type passwords. NEVERHANG + A.L.A.N.
Betterprompt MCP
4.1/10MCP server for AI-enhanced prompt engineering and request conversion.
Maxential Thinking MCP
4.1/1011 focused tools for structured thinking, branching, revision, and navigation.
Catalog Cli Pro
4.1/10Amazon catalog auditing tool. 13 quality checks for your listings.
Banana Prompts MCP
4.1/10MCP server to search Nano Banana prompts from bananaprompts.fun
Litellm MCP
4.1/10Access 100+ LLMs with one API: GPT-4, Claude, Gemini, Mistral, and more.
Veridion Nexus
4.1/10Veridion Nexus MCP server - GDPR Art. 44-49 runtime compliance for AI agents
Shodan
4.1/10MCP server for Shodan API — device search, IP lookup, DNS, and CVE/CPE queries.
Jupyter MCP Server
4.1/10A powerful MCP server for AI-driven Jupyter Notebook management and execution
Unified Offer Protocol
4.1/10AI-powered e-commerce product search, affiliate links, and price negotiation
Chrome Devtools MCP
4.1/10MCP server for Chrome DevTools
Clawallex MCP
4.1/10MCP Server for Clawallex payment API - Pay for anything with USDC virtual cards
Codealive MCP
4.1/10Semantic code search and analysis from CodeAlive for AI assistants and agents.
Riveter
4.1/10MCP server for Riveter's enrichment, scraping, and monitoring API
Omni Nli
4.1/10An MCP server for natural language inference
MCP Airq
4.1/10MCP server for direct HTTP communication with air-Q air quality sensor devices
MCP Airq Cloud
4.1/10MCP server for air-Q Cloud API — access air quality data from anywhere
MCP Server Couchbase
4.1/10Couchbase Model Context Protocol Server to interact with Couchbase clusters
Agentskb
4.1/10Researched knowledge for AI agents. Canonical answers from official sources.
Rocket Plus MCP
4.1/1056+ AI tools for CRM, content, workflows, SkillForge & marketing automation.
MCP Simulate
4.1/10MCP server for dry-run EVM transaction simulation via Crypto APIs
Windows MCP
4.1/10An MCP Server for computer-use in Windows OS
Guesty
4.1/10MCP server for Guesty property management — 38 tools for STR operations.
Build
4.1/10Structured build tool output (tsc, generic commands) as typed JSON diagnostics.
Cargo
4.1/10Structured Rust cargo operations (build, test, clippy) as typed JSON.
Docker
4.1/10Structured Docker operations (ps, images, logs, build) as typed JSON.
Git
4.1/10Structured git operations (status, log, diff, branch, show) as typed JSON.
Go
4.1/10Structured Go tool output (build, test, vet) as typed JSON diagnostics.
Http
4.1/10MCP server for HTTP requests (curl) with structured, token-efficient output
Lint
4.1/10Structured linting output (ESLint, format-check) as typed JSON diagnostics.
Make
4.1/10MCP server for Make/Just task runners with structured, token-efficient output
Npm
4.1/10Structured npm/pnpm operations (install, audit, outdated, list) as typed JSON.
Pare Search
4.1/10Pare Search ג€” Structured code search operations (ripgrep + fd) as typed JSON.
MCP Uptime Kuma
4.1/10A Model Context Protocol (MCP) server for Uptime Kuma version 2.
Defenter Proxy
4.1/10Real-time semantic security for AI coding agents and MCP tools
Connapse
4.1/10Self-hosted knowledge backend for AI agents with hybrid search and MCP tools
A Mem MCP
4.1/10Self-evolving memory system for AI agents
Simap MCP
4.1/10MCP server for SIMAP.ch - Swiss public procurement platform
MCP Filesystem
4.1/10Advanced filesystem operations with strict security boundaries for AI agents
Token Pilot
4.1/10Save up to 80% tokens when AI reads code via AST-aware structural reading
Weishaupt Wem MCP Server
4.1/10Control and monitor Weishaupt heating systems via the WEM Portal
Docapi
4.1/10Generate PDFs, screenshots, and documents via any MCP-compatible AI agent.
Graphql
4.1/10Turn any GraphQL API into MCP tools. Zero config, zero code.
Openapi
4.1/10Turn any OpenAPI/Swagger spec into MCP tools. Zero config, zero code.
Timergy
4.1/10Create scheduling polls, vote, and finalize times from AI agents.
Megalinter
4.1/10MCP server for running Ox Security MegaLinter via mega-linter-runner
Ssh Licco
4.1/10SSH Model Context Protocol Server - Enable SSH functionality for AI models
Boostedtravel
4.1/10Flight search & booking for AI agents. 400+ airlines, 75 free local connectors.
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.