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.
Ssh MCP Pro
4.5/10Secure MCP SSH automation server with policy controls, resources, prompts, stdio, and HTTP.
Kaggle MCP
4.5/10Safety-first Kaggle MCP — confirm-gated destructive ops, submission budget, injection-fenced.
Vidgrid
4.5/10Give an AI agent eyes for video: turn a clip into a numbered frame grid + transcript.
Prufa MCP
4.5/10The full Prufa QA agent over MCP: audits, flows, monitors, gremlin chaos, discovery.
Screenpipe MCP
4.5/10Search your local screen recordings, audio transcripts, and computer activity from screenpipe.
Oxcode
4.5/10PageRank-curated code intelligence for coding agents over an indexed source repository.
Dep Scout
4.5/10Help AI agents find and evaluate mature packages across 6 ecosystems instead of reinventing them.
Whetstone MCP
4.5/10U.S. public-records: business registration (KYB), filings, watchlist screening, federal awards.
Opn MCP
4.5/10MCP server for opn.onl: shorten links, analytics, branded QR codes, and link management.
Progi
4.5/10MCP-native workflow engine: teach agents your processes once, they execute them consistently.
MCP Server
4.5/10Browse the giftcardshop catalog and buy gift cards with Lightning over MCP. No account, no signup.
Myinvois MCP
4.5/10Malaysian LHDN e-invoicing (MyInvois) compliance rules: scope, validation, change-diffs.
Pash MCP Server
4.5/10Standalone MCP server with PASH compression. Saves ~87% LLM tokens via dynamic tool registration.
Termada
4.5/10Persistent, policy-controlled missions for AI agents operating local and SSH environments.
France Travail MCP
4.5/10Serveur MCP des API officielles France Travail : offres d'emploi, ROME 4.0 et ROMEO.
Fusion MCP
4.5/10Local Fusion MCP: panel->judge->synthesis on the Claude CLI subscription, no OpenRouter.
Deep Research MCP Server
4.5/10Web search, clean page reading & one-call research dossiers for AI agents. No API key.
Creator Seo MCP
4.5/10SEO MCP server for creators. Ranks Google Search Console opportunities by ad revenue, not clicks.
Appstoreconnect MCP
4.5/10App Store Connect for MCP clients: PPP pricing, subscriptions, TestFlight, reviews, reports & more
Mail Index
4.5/10Local-first, read-only MCP server for recall over your Gmail: search, contacts, threads, digests.
Posokanei MCP
4.5/10Unofficial read-only MCP server for Greek supermarket price data from PosoKanei.
Cartography
4.5/10MCP-first read-only discovery of your infra & SaaS landscape as MCP resources, tools and prompts.
Linkedin MCP
4.5/10LinkedIn for AI assistants — search, profiles, jobs, feed, messaging, and gated writes.
Saju MCP
4.5/10Korean Four Pillars of Destiny (Saju/Bazi): calculate, interpret, compatibility & daily fortune.
Agent Magnet
4.5/10Behavioral memory layer for AI tools. Learns preferences and context across Claude, Cursor, Codex.
Mailbox MCP
4.5/10Multi-account email MCP server for Gmail, IMAP, and JMAP: search, send, drafts, labels.
Telegram MCP
4.5/10Telegram MCP server: read, send, and search messages and manage chats via your account.
Realhands
4.5/10Lets Claude drive your REAL mouse, keyboard and screen - works in your own logged-in apps.
Bazi MCP
4.5/10OpenFate Bazi MCP with True Solar Time, Four Pillars, Da Yun, and branch interactions.
Bizdays
4.5/10Verified business-day math for AI agents: holidays + per-country weekends, not guesses.
Agent Toolbelt
4.5/10MCP tools for AI agents: fetch any URL as clean text, live crypto prices, review & bid drafting.
MCP Token Optimizer
4.5/10Cut LLM token costs: count tokens, estimate cost, slim prompts, and pick the cheapest capable model.
Myco Brain
4.5/10Self-hosted, source-traceable memory layer and MCP server for AI agents, on your own Postgres.
Magpie Search
4.5/10Federated local-first search across transcripts, files, KG, vectors and the web for AI agents.
MCP Server
4.5/10Debug a bad AI-agent run from your editor: which intent fails, at which step, and why.
Skill Builder MCP
4.5/10Search the skill-builder registry and auto-install skills for Claude Code, Cursor, and Codex.
MCP Server
4.5/10Economic-safety tools for trading agents: executable quote + rug/honeypot pretrade check via x402.
Xaps
4.5/10Pre-execution audit for autonomous agents. Independent receipt before irreversible actions.
Riv MCP
4.5/10Riv MCP server — a thin shell over the Riv authorization API (authorize, get_activity).
MCP Fiscal Brasil
4.5/10Ferramentas fiscais brasileiras: CNPJ, NF-e, IBS/CBS, ICMS, Simples Nacional, NCM/CFOP. Sem API key.
Eyebrowse
4.5/10Stealthy, LLM-drivable browser engine — a Python library + 85-tool MCP server on stealth Chromium.
Servicenow MCP Ai
4.5/10ServiceNow MCP server — 67 tools over the full REST surface, every auth method, flows, diagrams.
Umbriel
4.5/10See and drive a whole Windows machine from Bun — apps, input, screen, OCR, registry, OS — via MCP.
Legalithm MCP Server
4.5/10EU AI Act risk classification, obligations and Article 50 disclosures. Offline, no API key.
Memocall
4.5/10Recall past Claude Code conversations from any project as clean, compact Markdown.
Apple Stocks MCP
4.5/10Reads your macOS Apple Stocks watchlist, quotes and fundamentals locally. Read-only, no network.
MCP Plesk Lite
4.5/10MCP server for Plesk: manage domains, DNS, mail, SSL, backups, databases and WordPress via AI.
MCP Server
4.5/10Tools for floor plan validation, GLB checks, and 3D-print unit math — Ritn3D companion.
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.