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.
MCP Seo Audit
4.1/10Technical SEO site audit MCP: health score, issues, robots, sitemap, JSON-LD.
Agentram MCP
4.1/10Model Context Protocol server for AgentRAM. Persistent memory for AI agents.
Dead Letter
4.1/10Convert .eml email exports to Markdown with YAML front matter
Godot MCP Runtime
4.1/10Zero-addon MCP server for Godot 4: agents edit, run, and play-test the game.
Swing MCP
4.1/10MCP server for inspecting and automating Java Swing applications.
Glm MCP
4.1/10GLM (Zhipu/Z.ai) as a ~10x cheaper file-editing subagent for AI coding agents.
Ardupilot MCP
4.1/10Diagnoses ArduPilot DataFlash flight logs over the Model Context Protocol.
Contactapi
4.1/10An open-source API for collecting and managing contacts and signups.
Inhalt
4.1/10An open-source headless CMS for managing content models and entries.
Yourtraffic
4.1/10Open-source, privacy-first web analytics for tracking your sites' traffic.
Fittok
4.1/10Retrieve only the relevant code for a codebase question, within a token budget.
Qsys MCP
4.1/10Control QSC Q-SYS systems over QRC from AI agents or Claude.
Rlg MCP
4.1/10MCP server exposing rlg log streams to LLM agents via JSON-RPC 2.0 over stdio.
Aimarket Oracle Gateway
4.1/10Stdio MCP: 17 verifiable AIMarket oracles, 35 pay-per-call tools for AI agents.
Aimarket Plugins
4.1/10Stdio MCP packager: AIMarket hub plugins into self-hosted MCP server products.
Noc.Mcpserver
4.1/10MCP server exposing NiceOneCode's JSON-to-C# converter as an AI-callable tool.
Aisentinel
4.1/10Pre-tool policy enforcement + JSONL audit for AI agents. Apache 2.0.
Arkgate
4.1/10When your agent writes TypeScript, ArkGate stops it from breaking the layers.
Ida Pro MCP Fusion
4.1/10IDA Pro MCP fusion with cache queries and multi-binary headless analysis.
Boxadm MCP
4.1/10MCP server for Box admin-log analytics — external-sharing visibility, read-only
Korea Business Verify
4.1/10한국 사업자 검증 액션 MCP 서버 — 진위확인·휴폐업·과세유형·세금계산서 발행 가능 여부 (국세청 공공데이터 기반)
MCP Server
4.1/10Access the full Runware API as MCP tools: image, video, audio, 3D, and text.
Vercel Deployment MCP
4.1/10Reference MCP stdio server for observing Vercel projects and deployments.
Gitworthy
4.1/10is it worth your commit? Pre-flight triage for OSS contribution targets.
Gmail MCP Server
4.1/10Lean Gmail MCP server with auto authentication support
Amenbo
4.1/10Japanese-web-native MCP server for low-impact, token-efficient web collection
Deepthonk
4.1/10Provider-neutral OpenDeepThink reasoning server: generate, judge, rank, mutate.
MCP Eureka
4.1/10MCP server for Polish tax interpretations (KIS/MF) via EUREKA with citations.
Trello MCP Server
4.1/10Trello Model Context Protocol (MCP) Server for AI Agents
Smspm
4.1/10Send SMS via the SMSPM API from any MCP client.
Boo Mpp MCP
4.1/10Pay-per-call crypto data for AI agents. USDC.e on Tempo via MPP. No API key.
Boo X402 MCP
4.1/10Pay-per-call crypto data for AI agents. USDC on Base via x402. No API key.
Ariadne
4.1/10Deterministic local cross-service API-chain discovery for AI coding agents.
MCP Server
4.1/10Post and schedule across 9 social platforms from Claude, Cursor, or ChatGPT.
Personal Model
4.1/10Local-first personal memory and model server for trusted MCP agents on macOS.
MCP Camptocamp
4.1/10API Camptocamp.org : itinéraires alpins, sommets et points de passage.
Cgraphy
4.1/10Code knowledge graph over MCP: token-budgeted context for AI coding agents.
Observability Aiops
4.1/10Governed Prometheus + Grafana ops: PromQL, alerts, dashboards, RCA; 39 tools.
Wigolo
4.1/10Local-first web intelligence MCP server for AI coding agents
Agent Browser
4.1/10MCP server for browser automation via Vercel's agent-browser CLI
Google Adwords
4.1/10MCP server for Google Ads campaign and budget management
Google Analytics
4.1/10MCP server for Google Analytics 4 — reports, realtime data, and admin
Google Image
4.1/10MCP server for Google Gemini image generation and editing
Gpt Chat
4.1/10MCP server for the OpenAI ChatGPT API — chat, vision, and embeddings
Gpt Image
4.1/10MCP server for OpenAI GPT image generation and editing
Grok Image
4.1/10MCP server for Grok image generation and editing
Grok Video
4.1/10MCP server for Grok video — text-to-video, image-to-video, and video editing
Namecheap
4.1/10MCP server for Namecheap — check availability, list domains, and get pricing
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.