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.
Hundo
3.7/10Read your accounts, budgets and net worth, and draft changes you confirm.
Foliyo
3.7/10Create, brand, publish and track client-ready pages from your AI tools.
Bashoor Menu
3.7/10کافه باشور پیروزی مشهد: منوی زنده و قیمتها | Bashoor Cafe live menu and prices
Gamma Levels
3.7/10Free delayed gamma flip, call and put walls, max pain and net dealer gamma
Agent Tools
3.7/10Read-only US public-data screening tools with free Basic and Evidence tiers.
Docs
3.7/10Public read-only SYMBaiEX developer and agent documentation.
Timequip
3.7/10Manage Timequip projects, tasks, comments, members, and dashboards through MCP.
MCP Server
3.7/10Connect an AI assistant to a Capacities space (objects, daily notes, search).
Kelam
3.7/10Place and follow real phone calls and SMS through your Kelam voice agents.
Agent Layer
3.7/10Fixed-fee software consultancy. Ask about scope, terms, and live capacity.
Exploitwatch
3.7/10Check dependencies against CISA's real Known Exploited Vulnerabilities feed.
Site
3.7/10Calibvo: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Cookievo: the site's own MCP server — dataset; every answer cites the site.
Site
3.7/10Excurvo: the site's own MCP server — dataset; every answer cites the site.
Job Search
3.7/10Paid job search: 7 matched roles, each with a tailored CV and cover letter.
Site
3.7/10Lettza: the site's own MCP server — dataset; every answer cites the site.
Discovery
3.7/10Read SDUK Studio's published articles and book a provisional discovery call.
Site
3.7/10Stocktaka: the site's own MCP server — dataset; every answer cites the site.
Tabfleet
3.7/10Launch, inspect, control, and share isolated cloud browsers for your agents.
Site
3.7/10Wipvo: the site's own MCP server — compare; every answer cites the site.
Creator Studio
3.7/10Manage your Hotspot maps, spots and earnings from your AI assistant.
Slatemark
3.7/10Market data and analytics for external AI clients
Meridian
3.7/10Reliable macroeconomic and market data for AI agents via MCP
Roblox Trade Values
3.7/10Roblox trade values and trade fairness for MM2, Adopt Me and Flee the Facility.
Auditflag
3.7/10Search SEC EDGAR for going-concern auditor opinions in real 10-K/10-Q filings.
Cloakcheck
3.7/10Scan a page for hidden prompt-injection payloads targeting AI agents.
Renewalmatrix
3.7/10Score a subscription flow against US click-to-cancel / auto-renewal laws.
Stripecheckup
3.7/10Scan pasted Stripe webhook/checkout code for common integration bugs.
Triageshield
3.7/10Verify a vuln report's file/line/function claims against a real GitHub repo.
Commentlettercheck
3.7/10Look up whether a US ticker has SEC comment-letter correspondence on file.
Rewardsguard
3.7/10Spot-check a TikTok creator export for Creator Rewards disqualification risk.
Triageshield
3.7/10Verify a vuln report's file/line/function claims against a real GitHub repo.
Vercelpycheck
3.7/10Scan a public GitHub repo for known Vercel Python-runtime deploy footguns.
Maedong
3.7/10KOSPI/KOSDAQ daily signal lists with verified forward returns since 2020.
Agent Mail
3.7/10Inboxes, threads, drafts and sending, built for agents.
Creator Discovery
3.7/10Find creators from a seed profile or a brief, and look up their contact email.
Finance
3.7/10Prices, fundamentals, filings, crypto and prediction markets, for agents.
Public profiles, timelines, reels, highlights, comments and video transcripts.
Prediction Markets
3.7/10Live odds and markets from the major prediction markets.
Search every community or one of them, browse post streams, read comment trees.
Sales
3.7/10Find companies and the people who decide, enrich them, and size their market.
Seo Ai Visibility
3.7/10How a brand shows up in ChatGPT, Claude, Gemini and Perplexity answers.
Seo Apps
3.7/10App store listings, details, searches, reviews and app-store search results.
Seo Serp Other Engines
3.7/10Search results outside Google: Bing, Yahoo, Baidu, Naver, Seznam and YouTube.
Social
3.7/10What people post and say across the major social platforms, in one place.
Twitter Api
3.7/10Profiles, timelines, followers, replies, quotes, communities, lists and trends.
Web Search
3.7/10Web search and page extraction across several independent search providers.
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.