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.
Focus Space
4.3/10Create focus spaces and read user-authorized focus history summaries.
Xojo MCP
4.3/10MCP server for controlling the Xojo IDE on macOS
Ivygrep
4.3/10Local code search and task context packs for coding agents
Cmdop Care
4.3/10Read-only health and storage diagnostics for an enrolled CMDOP machine fleet.
Cursor Proxmox MCP
4.3/10Manage Proxmox VE via Cursor: QEMU, LXC, storage, HA, firewall, access.
Okf MCP
4.3/10Validate, search, graph, and safely author local Open Knowledge Format bundles.
Madar
4.3/10Authenticated local evidence paths for JavaScript and TypeScript coding agents.
Talamus
4.3/10Local-first, source-grounded memory that survives AI agent sessions.
N8N MCP Community
4.3/10A security-focused MCP server for self-hosted n8n Community Edition.
Assistant Widget
4.3/10Generate a paste-ready embed for a floating 3D avatar chatbot on any website.
MCP Server
4.3/10Affiliate attribution and commission data for iOS (StoreKit 2) and Shopify
Codehelper
4.3/10Local-first code intelligence MCP: symbol graph, impact analysis, 60+ tools.
Discord MCP
4.3/10Safe Discord access for reading guild data and optionally managing bot messages
Scan MCP
4.3/10MCP server for scanner discovery and batch capture via SANE
Atimelogger MCP
4.3/10MCP server exposing the ATimeLogger REST API (activities, reports, types)
MCP Odoo
4.3/10Odoo MCP: gated writes, multi-instance. Free hosted: ERPipe (mcp.erpipe.com)
Fartlek
4.3/10A coach's morning report from your Garmin data, for any LLM via MCP.
Macbeth
4.3/10Open-source computer use for macOS agents.
Openadapt Agent
4.3/10Local Beta bridge for governed openadapt-flow workflows and attended actions.
Openhcs
4.3/10Inspect, author, validate, and run high-content microscopy workflows.
Whisper Transcribe MCP
4.3/10Transcribe audio locally with faster-whisper or through the OpenAI Whisper API.
Truepane
4.3/10Local MCP server generating complete App Store & Google Play screenshot sets.
Bee Public
4.3/10Bee governed intelligence for chat, code, research, documents, and memory.
Kernel
4.3/10Verify consequential AI actions before they execute.
Searchforge
4.3/10Free open-source web search and page reading for LLMs, AI agents, and RAG.
Ai Slop Checker
4.3/10Deterministic offline scorer for AI-writing tells in text and landing copy.
Laguarde
4.3/10Self-hostable policy control plane for AI coding agents.
Icloud MCP
4.3/10stdio MCP for iCloud Calendar (CalDAV), with optional Contacts and Mail.
Gaggiuino MCP
4.3/10Remote MCP server for your Gaggiuino espresso machine's shots and profiles
Skeletongraph
4.3/10Zero-LLM structural code retrieval for AI coding agents, served over MCP.
Project Context Connector
4.3/10Give Claude complete understanding of your software project.
Throughline
4.3/10Give Claude complete understanding of your software project.
Diffctx
4.3/10Selects the minimum code an LLM needs to review a git diff
MCP Server
4.3/10Send SMS, MMS and WhatsApp, manage contacts and webhooks, from AI agents.
Render Useful MCP
4.3/10MCP server for the Render Public API: all 207 endpoints plus workflow tools.
Petromcp
4.3/10Local-first MCP server: read LAS well logs and DLIS files from your own disk.
Fetch Price
4.3/10Live UK marketplace product search with real prices and buy links.
Ingestion MCP
4.3/10Read-only MCP server for querying Kenda token spend and waste
Browser Game
4.3/10Local tools for planning and validating focused browser-game prototypes.
Zotero MCP
4.3/10Search, read, annotate, and add to your Zotero research library, local or web.
Memorix
4.3/10Local-first project memory with legacy MCP and 2026 discovery compatibility.
Countdowns Online MCP
4.3/10Live countdown timers for game launches, movie releases, sports and holidays.
Market Depth Lab
4.3/10Read-only Hyperliquid, funding-rate and cross-exchange perpetual spread tools.
Countdowns Online MCP
4.3/10Live countdown timers for game launches, movie releases, sports and holidays.
Ara Rgaa MCP
4.3/10Piloter des audits RGAA 4.1 sur Ara, référentiel embarqué. Non officiel.
Live Chemdraw MCP
4.3/10Connects AI assistants to a live ChemDraw window on Windows via COM automation.
Tinycontext
4.3/10Token-light local memory with SQLite hybrid retrieval for MCP agents.
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.