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.
Newsgurus Intel
4.1/10Pay-per-call trading intelligence for AI agents: live market regime, trading signals, composite conv
Clipzyn MCP
4.1/10Turn podcasts and long videos into ranked, finished short clips via the hosted ClipZyn API.
Fanvault
4.1/10Run storefronts, listings, orders, content, fulfillment, and analytics through AI.
Gluecron
4.1/10AI-native git hosting — repos, PRs, issues, CI gates, and AI code review over MCP (60 tools).
Hts Classify
4.1/10Classifies products into HS/HTS customs codes for import/export workflows. $0.10/call via x402.
Spoiler
4.1/10Sealed prediction-market verdicts, graded in public across Polymarket and Kalshi. No auth required.
Serpmantics
4.1/10French-first SEO: semantic content guides, scoring, E-E-A-T audits for Google, ChatGPT & Claude.
Vies Smoother
4.1/10SLA'd EU VAT validation on VIES. Honest 3-state result, never guesses. 100 free lookups.
Proof Of Human
4.1/10Prove a real, unique human performed an action; mint a signed, verifiable Proof-of-Human credential.
Context Company
4.1/10AI agent observability for production traces, natural-language insights, and improvement loops.
China Stocks
4.1/10China A-shares MCP. Keyless.
Cleo
4.1/10Log baby feedings, diapers, and sleep; manage family tasks, meals, recipes, groceries, and trips.
Jobctl
4.1/10Job application tracker for developers - AI agents write over MCP, you review in a dashboard.
The Floor
4.1/10Read & play The Floor, an on-chain strategy game on Robinhood Chain. Unofficial companion.
Changebook
4.1/10Your agent already broke this three times. ChangeBook tells it before the fourth.
Maeil
4.1/10Invite someone to a calendar event by phone number and get their real email back when they accept.
Sphere Marketplace
4.1/10One agent sells work, another buys it; delivery passes a gate and comes with a verifiable receipt.
Eval Engine MCP
4.1/10Pay-per-call AI evaluation MCP server. Score LLM outputs against benchmark rubrics via Workers AI.
Firmoscop
4.1/10Romanian company risk checks by CUI — verdict verde/galben/roșu from official public sources.
Agentic Ai
4.1/10Deal intelligence for agents: SEC-verified financials, validation, institutional deal scoring.
Rams
4.1/10Design review for UI code: 291 rules, scored 0-100 with fixes and git-applyable patches.
Simceptor
4.1/10AI-native mock API server with MCP. Create REST/SOAP mocks from Claude, Cursor, or Windsurf.
Agent Data Platform
4.1/10Video generation cost estimates across providers, with provenance, freshness, and confidence.
Alphalabs Intelligence
4.1/10Live trading-pipeline intelligence for AI agents: signal scoring, calibration, recorded outcomes.
Cpg Agent Protocols
4.1/10BPC Agentic Commerce Signals
Gitdealflow
4.1/10Track startup engineering acceleration from public GitHub data before funding rounds
Invisibleexit
4.1/10Faceless micro-SaaS system for employed professionals. Build $4K/mo without quitting
Unlocksaas
4.1/10Playbook engine: non-dev founders land first paying customer in 60 days or refund
Got Cosy Graph
4.1/10Travel/hotel data: 6,300 hotels scored for cosiness from guest reviews; verified booking links.
Sella
4.1/10Marketplace where AI agents buy datasets and API access, pay per call in USDC over x402.
Offers
4.1/10Merchant offers with validated discounts and no bought rankings; accepting mints a voucher code.
MCP Server
4.1/10CODENIVERSE Thai dev agency: services, company profile, and articles on AI agents and automation.
Jp Data
4.1/10Japan, Korea and UK official data for AI agents: filings, FX, weather, travel, patents, AI tools.
Whoisgenius
4.1/10Domain attribution and correlation for AI agents, with confidence and per-signal evidence.
Raze
4.1/10Explore Raze services, pricing, projects, availability, and confirmed introduction bookings.
Agenda Rio Br
4.1/10Agenda Rio — events and cultural agenda for Rio de Janeiro: shows, exhibitions, and things to do.
Agenda Sampa Br
4.1/10Agenda SP — events and cultural agenda for São Paulo: shows, exhibitions, and things to do.
Sipi Bot Spend Firewall
4.1/10Pre-spend firewall for AI agents. Approves, blocks, flags transactions against policy rules.
Summarize Vid
4.1/10Summarize YouTube videos or fetch transcripts. Pay-per-call via x402 (USDC on Base), no account.
Basinwise
4.1/10Determines which NPDES stormwater permit governs a US site and its requirements, cited to source.
Denialpath
4.1/10Deterministic CMS NCCI/MUE claim scrubbing and CARC/RARC denial explanations, cited to source.
Lodgedeck
4.1/10STR legality, permits and lodging tax by city, each field cited to its source jurisdiction.
Lmgram
4.1/10Consent-based human matchmaking for peer advice, collaboration, and practical help.
Status
4.1/10Live status and health checks for AI coding providers: Claude, Cursor, Copilot, Codex and more.
Au Hot Water Payback
4.1/10Heat pump vs gas hot water (AU): rebate stack, net outlay and payback verdict by postcode.
Job Board Operator
4.1/10Connect Claude, Cursor, Codex, and other MCP clients to manage your Cavuno job board.
Muze Cmo
4.1/10Run your ecommerce ads from Claude & ChatGPT: Meta, Google, Amazon, Shopify (150+ tools)
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.