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.
Jasswiki
4.5/10First production Authority-MCP. W3C VC attested by Jassverband Schweiz.
Well Being Check
4.5/10Hosted MCP app for guided anxiety, depression, and well-being self-checks.
Transcript Magic
4.5/10Generate transcripts from YouTube, TikTok, Instagram, and Facebook videos.
Rodin
4.5/10Find ~5 thinkers whose intellectual fingerprint matches a passage of text.
Notes
4.5/10Access your Cosmonote audio notes, transcriptions, summaries, and action items.
Taskforce
4.5/10Task and planning workspace for humans collaborating with AI agents
Scry
4.5/10Free IPv4 lookups against a distributed attacker-observation corpus.
Realestate
4.5/10Czech distressed real estate — anonymized district aggregates (k≥5). Free tier.
MCP Server
4.5/10KYB for AI agents: verify business registrations from MCP clients.
Seo MCP
4.5/10Six tools for SEO and AI-readability audits. 91 checks, 11 score modules.
Foodnear Me
4.5/10AI-native restaurant discovery with verified Menu Protocol data.
Taste MCP
4.5/10Expert review for AI agents. On-chain proof of human review.
MCP Server
4.5/10Hosted MCP server for live public-data APIs and Skills for AI agents.
MCP Server
4.5/10Official MCP server for Lovable, the AI-powered full-stack app builder.
MCP Server
4.5/10Connect agents to 6DuckLearn memory, approvals, and runtime control.
MCP Server
4.5/10Manage AI filmmaking projects, scenes, assets, and generations in Martini.
Intelligence
4.5/10Real-time Ethereum liquidation intelligence for AI agents and MEV bots.
MCP Server
4.5/10Eligibility-first UK & EU grant discovery, inside ChatGPT and Claude.
Appendix
4.5/10Physician-reviewed medical opinions and prescriptions for AI agents.
Forecasting
4.5/10Forecast future events and scan prediction-market edges.
MCP Server
4.5/10Send free or paid faxes to US/Canada from Claude, ChatGPT, and other AI agents.
Drop
4.5/10Publish web pages straight from your AI assistant and share them with a link.
Alloy
4.5/10AI workspace — shared knowledge, skills, and tools for AI agents
Token Gateway
4.5/10Remote MCP gateway for low-cost x402-paid GPT-5.5 and utility tools.
Food Logger
4.5/10Food logging, nutrition summaries, and meal photo calorie and macro estimates.
Htag Spatial
4.5/10HTAG H3 spatial tools for price/rent, indicators, geometry, and concordance.
Pagelive
4.5/10Publish pages straight from Claude as private, branded, tracked links.
String MCP
4.5/10Query STRING interactions, enrichment, annotations, homology, and PPI networks.
MCP Server
4.5/10Production-readiness for your AI coding agents.
Converly
4.5/10Set up and manage conversion tracking by chatting with your AI assistant.
Jellypod
4.5/10Create, import, and publish Jellypod podcast episodes from your AI assistant.
Bikefuchs
4.5/10Price comparison & cart optimizer for bike parts across German & Austrian shops
Revdoku
4.5/10Publish websites from AI agents using Revdoku buckets.
Otto Travel
4.5/10Plan, book, and manage business travel.
Flashcards
4.5/10Read and write open-source flashcards through split read/write MCP tools.
Hub
4.5/10Free public MCP for AI agents — 193 tools, 44 workflows. No API key.
Pubfi MCP
4.5/10Route crypto data needs through PubFi capability and gateway tools.
MCP Server
4.5/10Real-time U.S. medical license verification across all 50 states + DC.
Market Data
4.5/10Live Iran exchange rates, gold, crypto, and Toman market data for AI agents.
Donotact
4.5/10Fail-closed guard clause for prediction-market agents before trade().
Loop MCP
4.5/10L402 MCP: 5 paid BTC/Lightning tools + fiat credits, 10-25 sats/call.
Platform
4.5/10167 MCP tools, 64 playbooks. CRM, pastoral care, giving for churches.
Seraph
4.5/10Crypto transaction firewall and risk tools for MCP agents.
Time
4.5/10Clockchain®: neutral verified network time for AI agents (get_time). Testnet.
Roxels MCP
4.5/10Let AI agents create configurable voice agents via meeting rooms and return structured data.
Docqa
4.5/10AI document verification: catch hallucinations, arithmetic errors, and field mismatches.
Arc Security
4.5/10Scan AI agent skills for 25 attack classes + runtime monitoring. 1,316+ findings.
Bellwether MCP
4.5/10Live prediction market data from Polymarket and Kalshi with VWAP pricing and reportability.
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.