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.
Prismclip
3.9/10Create evidence-backed video clips from owned recordings through PrismClip's OAuth-connected MCP.
Readiness
3.9/10Scan website AI readiness, understand the result and route customers to the right SYA package.
Agent Commerce
3.9/10x402 V2 payment-to-access on Solana USDC with receipts, entitlements, atomic metering and webhooks.
Chat Thing
3.9/10Build and manage AI-native customer support agents from Claude or any MCP client.
State Transfer Tracker
3.9/10Whiteout Survival State Transfer tracker: phase dates, active status, remaining pass chances.
Iron City
3.9/10Sovereign AI agent economy: oracle-verified tools, escrow, arenas; paid in USDC on Base via x402.
Ai Visibility
3.9/10Free AI visibility scan for any B2B company: see how often AI engines recommend it, plus the fixes.
Flori Financial Data
3.9/10SEC EDGAR financials, insider trading, and economic data for AI agents. US GAAP + IFRS.
Fable Maker
3.9/10AI story generator — create illustrated storybooks, AI songs, and short AI video films
The Ultimate Critic
3.9/10Check AI work against requirements and return structured verdicts, findings, and repair steps.
Ipdefender MCP
3.9/10Trademark filing monitor across 40+ countries - detect filings that resemble your brand.
Reservations
3.9/10Remote MCP for TehProf Booking: browse resources & availability, create & cancel reservations.
Connect
3.9/10Find availability and book across a network of independent venues via your AI assistant.
Core
3.9/10Unified.to MCP server — one API for 500+ B2B SaaS integrations across 28+ categories
Knihajizd
3.9/10Czech mileage logbook (kniha jizd): AI journey drafts, statutory reimbursement, XLSX export
Ninoxnet
3.9/10Ninox ERP by NinoxNet: manage inventory, sales, HR and goals, and build in-app dashboards.
Obol
3.9/10Pre-trade safety verdicts for agents: token rug/honeypot, calldata guard, wallet risk — signed x402.
Noderooms Discovery
3.9/10Read-only NodeRooms Agent discovery, safety policy, public indexes, and arrival contract.
Issuefoundry Agent Market
3.9/10Discover agent services and buy IssueFoundry's fractional-cent x402 reliability utilities.
Edge Diagnostics X402
3.9/10Edge-based network diagnostic utility checking host latency, gated via x402 payment rails.
Anon Avantis Risk Lens
3.9/10Paid Base USDC lending decisions and rate-risk alerts, plus free risk and routing tools.
Grounded Aeo
3.9/10Audit and fix a site for AI citation + SEO, verify it, then publish a v=AEO1 record.
Solidus
3.9/10Solana pre-trade safety for agents: rug check, honeypot sell-sim, drainer scan, tx preflight.
Promptdna
3.9/10Community library of composable AI prompt blocks for search, composition, and contribution.
Agent Commerce
3.9/10AI-agent product catalog: search, lookup & purchase routing over verified merchant data.
MCP Server
3.9/10Create, update, and publish real hosted websites from your agent via the Aveiro API.
Mindset
3.9/10Semantic search over MINDSET's brand strategy topic database, plus its system prompt.
Tools
3.9/10Pay-per-call AI tools over x402: web research, summarization, structured extraction (USDC, Base).
Feedback Board
3.9/10The feedback board your AI agents work from: users vote, agents build over MCP. 22 tools.
Referral Exit Routes
3.9/10Read-only senior-care exit routes, duplicate-referral deadlines, and templates; no PII or sending.
Quiver Risk Brain
3.9/10Verifiable, deterministic risk math for autonomous agents; re-runnable proof on every answer.
Legal Grounding
3.9/10Experimental GDPR grounding: rules, preconditions, exceptions, exact quotes, and citation checks.
MCP Server
3.9/10145 microservices: PDF, DNS, captcha, scraping, screenshots, datahub, gas, tokens. USDC no KYC.
Statshawk
3.9/10Live sports stats and pre-computed analysis for AI assistants across NBA, MLB, NFL, and NHL.
Studiopro
3.9/10Personal asset search engine: everything you make or upload is searchable by what's inside it.
MCP Server
3.9/10Munich social media marketing agency: info, services, case studies, content search + lead intake
Agent Companion
3.9/10A place for agents to think out loud about blockers — often clarifies them. ~20s, intermittent.
Breeze
3.9/10Breeze project management: cards, to-dos, comments, time tracking and estimates.
Savedthat
3.9/10Search your saved videos by what was said. YouTube, Reels, and TikTok transcripts. Read-only.
I3Deploy
3.9/10Deploy & release tracking with native MCP — ask Claude what's in production and cut the release.
Agent Observatory
3.9/10Public MCP digital twin with synthetic systems and an agent firewall. No customer data.
Ai Visibility Monitoring
3.9/10AI-visibility monitoring for your brand across ChatGPT, Claude, Perplexity & Gemini.
Hibp
3.9/10Breach intelligence API: email search, domain monitoring, passwords and stealer logs.
Lamina
3.9/10On-brand product photos, model try-ons, video reels & banners from a brief + brand kit.
Book Cover Generator
3.9/10Generate genre-aware, print-ready AI book covers (ebook, KDP wrap, audiobook) via BeYourCover
Discovergpt
3.9/10REST API + MCP gateway for AI commerce: search, catalog enrichment, feeds/GEO, and virtual try-on.
Opentax
3.9/10Verifiable US tax oracle for AI agents: cited, machine-checkable federal and state tax computation
Wiki Private Law
3.9/10Answers, search and bank-complaint assessment for wiki.private.law by the Mothership runtime.
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.