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.
Site
4.1/10Roofing Quotes UK: the site's own MCP server — dataset, enquiry, entities (enquiry = a human...
Site
4.1/10Sauna Cold Plunge Compare: the site's own MCP server — dataset, enquiry (enquiry = a human...
Site
4.1/10Send A Parcel Compare: the site's own MCP server — dataset, enquiry (enquiry = a human handoff,...
Site
4.1/10Strength Standards Calc: the site's own MCP server — dataset, enquiry (enquiry = a human...
Site
4.1/10Structured Settlement Compare: the site's own MCP server — dataset, enquiry (enquiry = a human...
Carrier Records
4.1/10Dated motor-carrier records with receipts, verification, and specimens, from a records custodian.
Site
4.1/10Virtual Data Room Compare: the site's own MCP server — compare; every answer cites the site.
Monitors
4.1/10Know when cron jobs and AI agents stop running: create monitors and check in from your agent.
Human Approval Decision Gate And Shareable Result Page Publisher
4.1/10Followable agent result pages + human-in-the-loop yes/no approval gates before irreversible actions.
Coupures
4.1/10Coupures électriques signalées en France en temps réel : état par ville, département, stats.
Fairline
4.1/10Shops MLB, NHL, EPL and NFL lines across sportsbooks with a no-vig fair probability, for members.
Intelligence
4.1/10Flare and Songbird intelligence with provenance, source health, MCP access and x402 readiness.
Nibb
4.1/10Log meals, change portions, manage targets, and read trends in your Nibb food journal.
MCP Server
4.1/10Geopolitical risk score and theme board. Published kill criterion. Measured state, not forecasts.
Vibe2Text
4.1/10Audio & video to text, Russian-first: diarization, timestamps, summary, action items, subtitles.
Pdf Extract
4.1/10PDF text by page with hashes. 0.005 USDC/Base via x402. No OCR. Check /health for readiness.
Moretime
4.1/10Open agent discussion boards, private proposals and conversations. Participation is optional.
Catalog
4.1/10Бытовая химия и косметика «МылоПорошок» (Махачкала): поиск товаров, цены, остатки, корзина
Wall
4.1/10Receive and leave thoughtful anonymous traces on a quiet public wall for humans and AI agents.
Site
4.1/10Asbestos Survey Cost: the site's own MCP server — dataset, enquiry, entities (enquiry = a human...
Site
4.1/10SIM Only Deals Compare: the site's own MCP server — dataset, enquiry (enquiry = a human handoff,...
Bureau Public
4.1/10Bureau-operated public read-only MCP service for public Context Packets and Cases.
Intelligence
4.1/10Macro, market and decision intelligence over x402. Gaps are unavailable rather than estimated.
Construction
4.1/10Build & govern AI agents for regulated industries: EU/GCC residency, governance, audit.
Patent Data
4.1/10US patent status for agents: applications, office actions, owners, PTAB, claims, monitors.
Vokse
4.1/10Household budgeting app with AI assistant: zero-based envelopes, accounts, transactions, reports.
Order Eval
4.1/10Regression checks for Japanese order automations: six free cases, strict JSON scoring and CI gates.
Tenders
4.1/10TED procurement notices and changes for AI workflows, with source links, deadlines and freshness.
Slopcheck
4.1/10Score a YouTube channel's upload pattern against YouTube's inauthentic-content policy.
Studio
4.1/10Turn a script into a finished film: plan and quote free, then produce under a hard credit cap.
Accessproof
4.1/10Scan a web page's markup for the WCAG failures ADA demand letters cite most often.
Cloakcheck
4.1/10Scan a page for content planted to hijack an AI browsing/shopping agent before it acts on the page.
Marketaiverse
4.1/10A benchmarked market for AI agents: what runs on your GPU, trust checks, encrypted agent rooms.
Mission Quotes
4.1/10Quote a proxy-presence mission: what a real person on the ground in city X costs.
Rumbo
4.1/10Securely query and analyze business data, dashboards, projections, alerts, and knowledge.
Writing Studio
4.1/10Writing studio for novels and screenplays: read your projects and run cited fact-checks.
Semantic Reader
4.1/10Stateless TS/JS compiler facts for agents: references, imports, impact. No repo index or OAuth.
Nogogo Ai
4.1/10Check one French company by name or SIREN and get its Nogogo A-E reliability grade for free.
Biurko
4.1/10Polish invoicing and KSeF e-invoicing: issue, send, settle and file a company's documents
MCP Gateway
4.1/10Prove you made it first. Blockchain Timestamp creative work via Claude or any MCP-enabled AI Agent.
Crypto Market Data
4.1/10Spot prices, ranked market tables, history, OHLC, per-venue tickers and trending.
Equities
4.1/10US equities: prices, statements, ratios, earnings, estimates, filings and a screener.
Gtm
4.1/10One go-to-market set: companies, the people who decide, market size and social signal.
Seo
4.1/10Rankings, keywords, backlinks, site health and AI-answer visibility, several indexes.
Seo Backlinks
4.1/10Referring domains, anchors, links won and lost, and competitor link intersections.
Seo Content
4.1/10Where a brand or phrase is cited across the web, with trends, sentiment and ratings.
Seo Domains
4.1/10What a domain is built on and who owns it: technology detection and whois records.
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.