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.
Jbnu Lms Student
4.1/10전북대학교 학생의 공지, 과제, 마감, 제출 상태와 수업자료를 읽기 전용으로 정리하는 Windows/macOS 로컬 MCP 서버입니다.
Multimeter
4.1/10Scaffold, validate, format, and run YAML .mmt API tests. Do not invent syntax.
Weather
4.1/10An MCP server for weather information.
MCP Server
4.1/10MCP server for HTML2PDF Converter
Kronos MCP
4.1/10Stock price forecasting for China A-shares — Kronos K-line time-series model
Truesource MCP
4.1/10First-hand market signals: filings, procurement wins, R&D expansion, macro data
Sonicmatch MCP
4.1/10Analyze video mood and pace, then recommend license-safe BGM with a mix spec.
Dynamic Telegram Bot Api MCP
4.1/10A dynamic, self-refreshing MCP gateway for the complete Telegram Bot API
Chirak MCP
4.1/10Model Context Protocol (MCP) Server for Chirak Sales & Inventory Assistant
Memory Industry
4.1/10MemoryIndustry persistent memory MCP server: BM25+MMR retrieval and audit.
Razor
4.1/10Cut 95% of framework noise and token bloat from error logs for AI agents.
Chronoguard
4.1/10Deterministic temporal and business-date arithmetic for AI agents via MCP.
Interbanking
4.1/10Saldos y movimientos bancarios de Interbanking (Argentina). Solo lectura.
Tkach Security
4.1/10Fail-closed MCP adapter for untrusted model output over a local Tkach runtime.
Tauri Docs MCP
4.1/10Read-only MCP server for official Tauri 2 documentation snapshots.
Vsix Publish Lint
4.1/10Find the package.json lines that stop vsce before you run the release build
Vibo MCP
4.1/10Persistent memory for AI agents: L1/L2/L3, web compression, threads.
Riverside Fm MCP
4.1/10Riverside API surface as MCP tools.
Agentfem
4.1/10Build, run, inspect, and verify finite-element simulations with AgentFEM.
Codebase Chat
4.1/10Local-first codebase intelligence: cited answers, audits, reports. EN/FR.
Slowave
4.1/10Local adaptive memory for AI coding agents through a five-tool MCP lifecycle.
Arca Agro
4.1/10Cartas de porte, padron y comprobantes de ARCA (Argentina). Solo lectura.
Hotelbooking
4.1/10RollingGo Hotel Booking MCP Server (国内中文版)
Hotelbooking Ai
4.1/10RollingGo Hotel Booking MCP Server (Global/AI Edition)
Sw Dev Knowledge Base MCP
4.1/10Read-only offline MCP server over a curated Shopware developer knowledge base
Alternativespe MCP
4.1/10Private-market data across Southeast Asia via the Alternatives Partner API v3
Vps Guardian MCP
4.1/10Secure SSH bridge for AI agents to observe and safely administer Linux VPSs.
Agent Pattern MCP
4.1/10MCP server that provides AI agent pattern expertise for designing agent systems
Github Repo MCP
4.1/10MCP server for GitHub repo health, commit summaries, issue triage, and RAG Q&A.
Eco Router MCP
4.1/10Rank AWS, Google Cloud and Azure regions by grid carbon intensity and latency.
Coador
4.1/10Evidence-backed Android repository knowledge for humans and AI agents
Agentos
4.1/10Local-first persistent memory MCP server for AI coding agents.
Super Trouper
4.1/10MCP server for the Frida reverse engineering toolkit.
Ultra E2E Test
4.1/10List, create and move tasks through todo, in progress and done.
Facturae Verifactu Lint
4.1/1018 reglas sobre tu XML Facturae antes de que FACe lo devuelva
Gdpr Privacy Notice Lint
4.1/1016 rules read your privacy.md the way Articles 13 and 14 read it
Impressum Lint De
4.1/1017 Regeln mit Stichtag für Impressum, Footer und Shop-Templates im Repository
Sepa Pain001 Reject Lint
4.1/10Find the lines your bank will refuse before you send the batch
Terraform Provider Pin Lint
4.1/10Finds the .tf lines a clean terraform init is still free to move
Matlab MCP Server
4.1/10Connect AI coding agents to MATLAB. Run code, tests, and analysis via MCP.
Pursers
4.1/10Coordinate AI-agent work on a local-first, owner-controlled MCP board
Upres Cli
4.1/10UpRes MCP: list models, credits, submit 4K image and video upscale jobs.
Canal De Denuncias Lint Es
4.1/10Revisa la política de tu canal interno de denuncias, artículo por artículo
Coverage Gate Lint
4.1/10Finds the coverage gates in your repo that can never fail a build
Freelance Act Order Lint Jp
4.1/10発注書1通を21ルールで検査し、支払サイトの日数まで計算する
Renpy Release Gate
4.1/10Find the .rpy lines that compile clean and only break inside a player's save
Security Txt Cra Lint
4.1/1013 rules that decide whether a vulnerability report ever reaches you
Cuemap MCP
4.1/10Local memory and context retrieval for AI agents through CueMap.
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.