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.
Mons
3.7/10Find your next endurance challenge and train for it with your MONS coach.
Platform
3.7/10Webhooks, streaming and the AI interpretation endpoints.
Psychological
3.7/10Archetypes, Jungian typology, shadow work and the relationship-style readings.
Relationships
3.7/10Synastry, composite, compatibility scores, family dynamics and pet charts.
Reports
3.7/10Sixteen finished PDF reports and the white-label configuration behind them.
Ai Star Co Jp
3.7/10株式会社アイスター商事の公式サイトです。（ai-star.co.jp の内容を検索して答える。ヨミタス経由）
Surf
3.7/10Nearest NOAA buoy readings, tides and 7-day swell forecast for 150+ surf spots.
Static Md
3.7/10Markdown notes and whiteboards your AI agent can read and write.
Agents
3.7/10Find and message the AI agents of people and businesses at their fone.me links.
Multivoice
3.7/10AI dubbing, subtitles, transcription and media localization for AI agents.
Vocasa
3.7/10Rental property analysis your AI can call
Gdw
3.7/10NFL game-window weather calls: FLAG, WATCH, CLEAR, or DOME.
Commons
3.7/10Open, vote-ranked forum, Q&A knowledge base and inbox for AI agents
Pylon Seo
3.7/10Audit, rank-track and analyze SEO for sites via an authenticated MCP server.
Dpa
3.7/10Data processing agreement, $350 flat fee, reviewed and released by a lawyer.
Specs
3.7/10Specs of commercially available robots, each figure citing its source document.
Responsehub
3.7/10Answer security questionnaires and RFPs from your AI knowledge base.
Caliper
3.7/10Build datasets and rubrics, then run evals that score your AI in Caliper.
Compass
3.7/10Read and update your Compass map: pages, changes, opportunities and interviews.
Ledger
3.7/10Log decisions with expectations, add evidence, and track metrics in Ledger.
Workbench
3.7/10Build, run and publish Workbench flows, tasks, shims and knowledge bases.
Xingdao Manage
3.7/10制造业管理工具箱：TBP问题解决/品质管理/TPM设备保全/J成本改善/OEE计算/活力组织诊断。一句话出成品报告。
Oddly Corpus
3.7/10The world, on the record. AI infrastructure built on the observed web.
Forecall Kb
3.7/10Known MCP tool-call failures and workarounds verified by reproduction.
Millstead
3.7/10Build and run your business with a conversation. Invite-only alpha.
Vozora
3.7/10Manage Vozora VPS servers, SSH keys, firewalls, DNS and usage from an AI agent.
Shadowgraph
3.7/10Pay-per-call causal market intelligence for AI agents via MPP.
Dealscore
3.7/10For AI agents: grade a used car's asking price vs live market comps.
Nimtin
3.7/10Book venues and vendors for events. Drafts wait in nimtin for you to send.
Ops Audit
3.7/10Read-only audit of a restaurant's public Google, website, and Yelp listings.
Autron
3.7/10Read and manage the Amazon Ads accounts connected to Autron.
Findings
3.7/10Validated API and app vulnerability findings with remediation guidance.
Rssa
3.7/10Read, verify and validate RSS-A signed agent feeds and groups (RSS for Agents).
Recolor The Past
3.7/10Colorize and restore photos, manage the library, and use account credits.
Shesmydoglady
3.7/10Book with ShesMyDogLady: services, prices and open times. No key needed.
Priomate
3.7/10Read-only access to your Priomate tasks, notes, inbox and team projects.
Productbyte
3.7/10Social posts, ads and insights for e-commerce. One connection for your agent.
Rentalcal
3.7/10Find direct-booking vacation rentals, check availability, and get stay quotes.
MCP Server
3.7/10Query cap table, share schemes, rewards and governance data held in Vestd.
Registrar
3.7/10Find, register, and manage domains from any AI chat or agent
Switchboard
3.7/10Agent to agent calls across AI apps. Humans remain in authority.
Dalea
3.7/10Plan, write and analyze Instagram and TikTok content using your Dalea account.
Coworking
3.7/10Find beauty workspaces in Munich and rent them at your approved personal rates.
MCP Server
3.7/10Reliable one-off and recurring HTTPS callbacks for apps and agents.
Laterbase
3.7/10A shared backlog for the out-of-scope work your coding agents find.
Agent Economic Trust
3.7/10Outcome-calibrated economic trust gate for autonomous agents.
Prenotazioni
3.7/10Servizi, giornate speciali e prenotazioni della Farmacia Santa Croce.
MCP Server
3.7/10MCP server providing OpenFeature SDK installation guides and OFREP flag evaluation
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.