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.
Glovebox MCP
4.7/10Sandboxed computer-use for AI agents: drive real browser + desktop apps in nested X11 windows
Lens MCP
4.7/10Deterministic navigation maps over code + markdown + Prisma for AI agents: 13 MCP tools
Standardgraph
4.7/10158,000+ K-12 education standards across 300 curriculum systems, cross-referenced via NLP.
MCP Gera Data
4.7/10Discover & query Gera's 30 attested open UK/US government datasets, each with signed provenance.
MCP Gera Indices
4.7/10Discover, resolve & cite Gera named UK NHS/OGL public-data indices with real source provenance.
Demipass
4.7/10Credential custody for agents: use secrets blind (ssh/http/smtp/git/db), never in context.
MCP Server
4.7/10Search 276,000+ open source icons and insert them as SVG or React components while you code.
MCP Server
4.7/10Spec-first code generation: OpenAPI, GraphQL, Protobuf, and SQL to typed clients in 11 languages.
Minipainter
4.7/10Local-first miniature-paint inventory and cross-brand color matching for AI agents.
Context Autopilot
4.7/10Mines your Claude Code and Cursor sessions into evidence-based CLAUDE.md / AGENTS.md rules.
Kaval
4.7/10Give AI agents action-bound proof packets and ALLOW/BLOCK/REVIEW gates for live facts.
Japan Data MCP
4.7/1030 tools for Japanese data: address, furigana, transit, Diet, holidays, weather, corporate registry
MCP Gateway
4.7/10Universal MCP gateway with Meta-MCP discovery, routing, and REST API capabilities.
MCP Server
4.7/10Discover, inspect and call ranked external data & tool APIs with unified billing and usage audit
Agent Readiness Auditor
4.7/10Audits any website for AI agent readiness and safety, scoring prompt injection risk and llms.txt.
B1Brain Wiki
4.7/10Curated GitHub repo corpus with DaVinci insights. Featured=deep analysis; Overview=orientation.
Searchts
4.7/10Keyless web access for AI agents: read bot-walled pages as Markdown, search, grab assets
Aifordatabase MCP
4.7/10Query any database in plain English or SQL through a guardrailed, read-only data layer.
Auravms MCP
4.7/10Create RFQs, compare supplier quotes with L1/L2/L3 ranking, and place purchase orders.
Goodmemory
4.7/10Durable user/project memory for MCP clients: recall context and remember selected facts.
Handoff MCP
4.7/10Cross-session memory for Claude over MCP — prioritised briefs, supersession, cross-project recall.
Thailand Data MCP
4.7/10Thai data for AI agents: DBD company-registry lookup, address normalization, holidays, VAT/WHT.
Vigilis MCP
4.7/10Gate AI-written tests: heal safe drift, refuse to hide real bugs, sign a verifiable receipt.
Klaws
4.7/10Scan code for Korean compliance risks — PIPA/개인정보보호법, Network Act, Credit Info. Not legal advice.
Openinsurance Wiki
4.7/10Open, source-cited knowledge base of Belgian insurance products: search, compare, verify, overlaps.
Keel
4.7/10Catches your AI coding agent when it games the tests - locked-test hashes, tamper detection.
Fortress
4.7/10Stealth browser for AI agents: fetch pages behind Cloudflare/DataDome/CAPTCHA, extract clean data.
Llm Usage MCP
4.7/10Local-first, multi-provider tool that captures LLM API spend and exposes it to coding agents via MCP
MCP Server
4.7/10Read your Clipy screen recordings: search, transcripts, AI summaries, and key moments with frames.
MCP Server
4.7/10MCP server for Sonenta translation management: keys, translations, a11y, and source-health tools.
Filechanger
4.7/10Convert documents between text formats (markdown, html, and more) via the FileChanger API.
Getabrain
4.7/10Real human judgment as agent tools — ask a question, get a structured human answer back.
MCP Server
4.7/10EDI parse, validate, send & inspect (X12/EDIFACT) from any MCP client. Demo without API key.
Stelar Signals MCP
4.7/10Crypto market-signal MCP tools (regime, sentiment, price, risk) via RapidAPI. Needs RAPIDAPI_KEY
Image Reader MCP
4.7/10Evidence-first image MCP. Agent Media Twin with metadata and citeable OCR evidence.
Video Reader MCP
4.7/10Evidence-first video MCP. Timeline document with ffprobe streams and subtitle cues.
Tarotoo MCP Server
4.7/10All 78 tarot card meanings (Rider-Waite-Smith): lookup, search, yes/no answers, and random draws.
Hotato
4.7/10Find where your voice agent talks over callers, and keep it from coming back. Offline, MIT.
Vocce Agent
4.7/10Transcribe audio/video to text + SRT/VTT via vocce's hosted Whisper. No API key required.
Artifacts
4.7/10Self-hosted artifact publishing: POST HTML/JSX/Markdown/zip, get an unguessable URL on your domain
Aicanvas
4.7/10Browse and install 75+ free animated, shadcn-compatible React components from AI Canvas.
Wallettriage MCP
4.7/10Real-time exploit-exposure risk check for EVM wallets, paid per query via x402 (USDC on Base).
Hub Equity MCP
4.7/10Standardized, restatement-aware SEC + European (ESEF) XBRL fundamentals, served to your agent.
Adr MCP
4.7/10MCP server for Architectural Decision Records: navigate, author, validate, link, and analyze them.
Conventionsense
4.7/10Git-history hole detector: flags files and C# members that co-change with your edit but are absent
Aibvf MCP
4.7/10AI BVF: score AI portfolios Stop/Fix/Accelerate with decision confidence and pace-layer drag.
Rrdoctor
4.7/10Deterministic Artifact Evaluation preflight and run-path grader for research repositories.
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.