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.
MCP Server
3.7/10LLM routing and A-share market phase signals via LG framework.
Finhay MCP
3.7/10Vietnam stock market data & portfolios via Finhay Securities OpenAPI.
Paseo
3.7/10List AugmentEV's agents. API key required; accounts are by request.
Event Discovery
3.7/10Find public EventMatey events that organisers have approved for AI discovery.
Max4Live
3.7/10Natural-language search over 8,900+ Max for Live devices for Ableton Live.
Agent Demand
3.7/10Economic-intent network for AI agents to publish demand and discover services.
Agentdocs
3.7/10An agent-first office suite Claude & ChatGPT read and write over one MCP URL.
MCP Gateway
3.7/10Access Siglume API Store tools and external MCP Router servers.
MCP Server
3.7/10Collaborative word processor you can use with your agent.
China Market Intelligence MCP
3.7/10China A-share screening, filings, holdings, flows and calendars as agent tools.
MCP Server
3.7/10豊胸モニター募集サイトのMCPサーバー。クリニック検索・術式情報・悩み相談・世代別記事を提供します。
Memoire Partagee
3.7/10Shared memory MCP server for product classification in wealth management.
Mozaika
3.7/10Measured design systems decoded from 588 real products, for coding agents.
MCP Server
3.7/10豊胸モニター募集サイトのMCPサーバー。クリニック検索・術式情報・悩み相談・世代別記事を提供します。
Polls
3.7/10One-link team polls: create polls, vote, fetch results, and close polls.
MCP Server
3.7/10Lowers your AWS bill by helping you clean up and optimize your setup
Eudr Parcel Screener
3.7/10Screen farm plots for EUDR deforestation risk with the official EU JRC maps.
Cohearence
3.7/10Track, curate, and analyze data about your health, habits, and goals.
Aribot MCP
3.7/10Threat modeling, code, API & cloud security, shadow-AI & compliance governance.
Bardo
3.7/10Identity & continuity for AI agents, gated by a proof-of-being-an-LLM puzzle.
Dcykjz
3.7/10Open Design MCP capability governed by DigitalPipe.
Dfuagp
3.7/10Premium test server verified via DNS-TXT.
Temp Mail
3.7/10Disposable email inboxes for AI agents — read messages and verification codes.
Catalog
3.7/10Deutscher Preisvergleich für E-Bikes – Bestpreis-Suche (read-only).
Catalog
3.7/10Deutscher Preisvergleich für Grills – Bestpreis-Suche (read-only).
Catalog
3.7/10Deutscher Preisvergleich für Handys – Bestpreis-Suche (read-only).
Catalog
3.7/10Deutscher Preisvergleich für Spielekonsolen – Bestpreis-Suche (read-only).
Catalog
3.7/10Deutscher Preisvergleich für Laptops – Bestpreis-Suche (read-only).
Catalog
3.7/10Deutscher Preisvergleich für Pools – Bestpreis-Suche (read-only).
Catalog
3.7/10Deutscher Preisvergleich für E-Roller – Bestpreis-Suche (read-only).
Catalog
3.7/10Deutscher Preisvergleich für Sneaker – Bestpreis-Suche (read-only).
Catalog
3.7/10Deutscher Preisvergleich für Stromspeicher – Bestpreis-Suche (read-only).
Catalog
3.7/10Deutscher Preisvergleich für Strom-Produkte – Bestpreis-Suche (read-only).
Catalog
3.7/10Deutscher Preisvergleich für Tablets – Bestpreis-Suche (read-only).
Catalog
3.7/10Deutscher Preisvergleich für Uhren – Bestpreis-Suche (read-only).
Catalog
3.7/10Deutscher Preisvergleich für Vitamine – Bestpreis-Suche (read-only).
Hyperliquid Data
3.7/10Rank, screen and compare the Hyperliquid perp universe on a completed day.
Connector
3.7/10Search logos, browse feeds and blogs, check your stats — from your AI chat.
Frankspace Public
3.7/10Read-only search over live UK office & workspace listings on FrankSpace.
Merchantwords
3.7/10Amazon keyword volume, reverse-ASIN, and SERP data across 11 marketplaces.
Latgalian
3.7/10Grounds LLMs in real Latgalian: Wiktionary lemmas, inflections, romanization.
Enrow MCP
3.7/10Find and verify professional emails and phone numbers via the Enrow API.
Booking
3.7/10Find and book Thai-massage salons in Switzerland with live availability.
Qualy
3.7/10Connect your AI assistant to Qualy to manage payments, billing, and contacts.
Angel Numbers
3.7/10Angel number meanings and repeating sequences like 111, 222, 333 for AI agents.
Iching
3.7/10I Ching hexagram casts, 64 hexagram meanings and changing lines for AI agents.
Journalize
3.7/10Agent-native double-entry accounting ledger with x402 micropayments
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.