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.
Whmcs MCP
4.3/10Connect Claude, ChatGPT, and Cursor to live WHMCS over MCP.
Statement Of Account
4.3/10Statements of account, aging buckets and dunning letters from your invoices.
Open Transcribe MCP
4.3/10Provider-independent speech-to-text with normalized transcripts over MCP.
Carve MCP
4.3/10Parse, lint, format, render, and migrate Carve documents through MCP.
Agenthub Monitor
4.3/10Renders a pipeline DAG and test-harness dashboard inline as an MCP App
Bookmcp
4.3/10Cited book knowledge for agents working on system design and implementation.
Reclip
4.3/10Inspect and download authorized media or precise clips locally with yt-dlp.
Ghostfox
4.3/10Self-hosted stealth browser for AI agents: Firefox engine + Rust MCP runtime.
Zeus Dev Helper
4.3/10Coach first Zeus Client app to green (stdio MCP).
Kosis Openapi MCP
4.3/10Korean official statistics (KOSIS) — tables, metadata and observations
Sift
4.3/10Runs a command, keeps every byte on disk, returns only the lines that matter
Kleinanzeigen
4.3/10A read-only, robots-clean MCP server over kleinanzeigen.de
Opsdoctor
4.3/10AI-powered CRM diagnostics, workflow audits, and industry benchmarks for SMBs.
Comunio
4.3/10Read and operate a Comunio fantasy football team: squad, market, offers, lineup
Diagrams MCP Server
4.3/10Local-first MCP server for PlantUML and Mermaid diagrams with drift detection.
Copilot Studio MCP
4.3/10Build, test, ship and maintain Microsoft Copilot Studio agents from the editor
Ovrin MCP
4.3/10Secure Linux sandboxes for AI agents, as MCP tools.
Ontology Atlas
4.3/10Read and write one codebase ontology kept as Markdown in the repository.
Gitee MCP Server
4.3/10让 AI 用自然语言管理 Gitee 仓库：查 star、管 Issue、基于 commit 生成中文 CHANGELOG（原生无此 API）
Factura Luz
4.3/10Lee y explica facturas de la luz españolas (QR de la CNMC). Todo en local.
Chestny Znak MCP Ru
4.3/10API Честного знака в ИИ-ассистенте: коды маркировки, эмиссия в СУЗ, отчёты
Diadoc MCP Ru
4.3/10API Диадока в ИИ-ассистенте: документы ЭДО, контрагенты, подписание, МЧД
Hh MCP Ru
4.3/10API hh.ru в ИИ-ассистенте: вакансии, отклики, резюме, статистика зарплат
Ozon MCP Ru
4.3/10API Ozon Seller в ИИ-ассистенте: товары, заказы, цены, остатки, финансы, отзывы
Sbis MCP Ru
4.3/10API СБИС (Saby) в ИИ-ассистенте: документы, этапы ЭДО, подпись, сертификаты
Vk MCP Ru
4.3/10VK API в ИИ-ассистенте: товары, сообщества, реклама, диалоги, статистика
Wildberries MCP Ru
4.3/10API Wildberries в ИИ-ассистенте: продажи, остатки, карточки, цены, отчёты
Yandex Market MCP Ru
4.3/10API Яндекс Маркета в ИИ-ассистенте: заказы, товары, цены, отчёты, отзывы
Daube Agent Bridge
4.3/10Universal AI skill compiler and MCP bridge. Write once, run across agents.
Seleniumbase
4.3/10Stealthy browser automation, testing, and web-scraping via CDP Mode.
Appletv MCP
4.3/10Local MCP server for semantic Apple TV control with optional screenshots.
Deadlatch
4.3/10Local advisory pre-trade risk gate for agents. Never places orders.
Avito MCP Ru
4.3/10API Авито в ИИ-ассистенте: объявления, чаты, заказы, автозагрузка, отзывы
Openreflex
4.3/10Optional diagnostics MCP server for OpenReflex's ambient project muscle memory.
Json Chamber MCP
4.3/10Two-key JSON seal/open. Cloak needs a live license. Open is keys-only.
Tillbooks
4.3/10Swiss accounting your agent can actually use: the TILL ledger over MCP.
Korean Patent MCP
4.3/10특허 검색이 아니라 존속 판정: 특허·실용신안 번호가 지금도 유효한지 등록원부 연차료까지 대조해 소멸 사유와 함께 알려줍니다
Gflow Cli
4.3/10Drive Google Flow from an agent: Veo video and Imagen image generation
Deixis
4.3/10Typed LSP operations for MCP clients.
Session Steward
4.3/10Review and safely clean local Codex and Claude Code sessions
Google Calendar MCP
4.3/10Google Calendar over MCP: calendars, events, recurrence and availability.
Xbbg MCP
4.3/10Local Bloomberg tools for xbbg users.
Ephemora Cell MCP
4.3/10WASM sandbox for MCP tools. WASI-isolated, fuel/memory/I/O capped, attested.
Capsolver MCP
4.3/10MCP Server for CapSolver - captcha-solving capabilities for AI agents
Contractgate
4.3/10Infer, dry-run, deploy, and inspect ContractGate semantic data contracts.
Hermes Prime
4.3/10Read-only stdio MCP server for a versioned convention card in Claude Code.
MCP Server
4.3/10payware A2A payments API for merchants, ISVs and payment institutions
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.