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.
Pk Eli MCP
4.5/10MCP server for Pakistani law: search and cite federal statutes and Supreme Court judgments.
Loom
4.5/10Local-first personal knowledge base. Cited answers from your vault via vector + graph retrieval.
Youtube Research
4.5/10Citation-ready YouTube transcript research and optional channel intelligence for AI agents.
MCP Local Rag
4.5/10Semantic code & doc search with keyword boost. AST code nav, auto HF mirror, local, privacy-first.
Beacon MCP
4.5/10Search 17,900+ open-source AI agents by capability, ranked by GitHub traction. Free, no key.
Graylog MCP
4.5/10Query logs from Graylog: get streams, search messages, aggregate, and get full data.
Kireo
4.5/10Long-term memory for Claude Code, Cursor and any MCP client, with a searchable web dashboard.
Au Eli MCP
4.5/10MCP server for Australia's Federal Register of Legislation: search and cite Commonwealth Acts.
Jp Eli MCP
4.5/10MCP server for Japan's e-Gov law search API: search, fetch, and cite national legislation.
MCP Server
4.5/10Daily AI-ranked stock, crypto, and macro research data from the Top 5 Stocks API.
Claude Chat
4.5/10Anthropic Claude Messages API MCP server — chat, vision, web search, extended thinking
Klaket MCP
4.5/10Let AI agents watch videos: local transcripts, speakers, scenes, chapters and moment search
Alertlogic MCP
4.5/10MCP server for Alert Logic MDR — incident response, log search, SOAR, and SOC workflows
Scrivener MCP
4.5/10MCP server for Scrivener: read, write, analyze, and search your manuscripts with AI assistants.
Stock Sentinel
4.5/10US stock attack/defense macro signals: 4-dimension framework, 26-year backtested. Research only.
Memex
4.5/10Local-first second brain with semantic search. Markdown notes indexed by a local ML model.
Llmstxt Doc Search
4.5/10BM25 search over llms.txt doc indexes (Strands, Kiro, AWS); sources addable at runtime.
Entra News Podcast
4.5/10Search Entra.Chat podcast transcripts — Merill Fernando's Microsoft Entra podcast on YouTube
Microsoft Ai Roundup
4.5/10Search Merill's Weekly Microsoft AI Roundup (msai.ms) archive — curated weekly Microsoft AI news
Tabler MCP Server
4.5/10Tabler.io for AI assistants: search 5,000+ icons, UI components, layouts, themes and docs.
Airas
4.5/10Automated AI research toolkit: hypothesis generation, experiments, and paper writing
Cartographer
4.5/10Governance MCP server for agent-maintained knowledge bases (OKF): git-backed writes, search, lint.
Infimium
4.5/10Private AI context layer for semantic code search, dependency graphs, memory, and workspaces.
Market Intelligence
4.5/10Equity trend, relative-strength, expected-return, market-context, and research resources for agents.
Brmarket MCP
4.5/10FREE Brazilian marketplace search (ML, Shopee, AliExpress) + import-tax calculator (x402)
Gtasks MCP
4.5/10Manage Google Tasks via MCP: list, search, create, update, move, and clear tasks.
Webfetch
4.5/10Self-hosted web search for LLM agents: search -> fetch -> rank pipeline with semantic caching
Doc MCP Server
4.5/10Offline MCP server for local Qt 4.8, Qt 5, and Qt 6 documentation with full-text search.
Anilist MCP Server
4.5/10MCP server for the AniList GraphQL API — anime/manga search, details, and personal list management.
Mailwarden
4.5/10Gmail MCP server for email triage: search, labels, archive, trash, unsubscribe, snooze.
MCP Server
4.5/10Read, search, edit and branch Translatize translation labels and fill missing translations.
Ghostlink
4.5/10Sandboxed repo access for coding agents: search, read, patch, run, git -- confined to a repo root.
Shopify Geo Audit
4.5/10Audit any Shopify store for AI search (GEO/AEO) readiness and generate the fixes. No signup.
Cn Scraper MCP
4.5/10MCP server for AI agents to search major Chinese internet platforms with local-first login support.
Yandex Lavka MCP
4.5/10Unofficial MCP server for ordering Yandex Lavka groceries: search, cart, checkout.
Misakanet
4.5/10Failure-memory layer for coding agents: search evidence-rated failure lessons by error text.
Openim
4.5/10Read-only OpenIM search for institutional buy-side investment models and architecture.
Reuse Before Generate
4.5/10Checks whether your idea already exists before your agent builds it. Searches GitHub, npm, Python.
MCP Server
4.5/10Search TradeSearcher strategies and backtests from Claude Code, Cursor, Codex, and other agents.
Images MCP
4.5/10Search and download stock images from Unsplash, Pexels, Pixabay, Freepik, StockVault, and Burst
Tacitus MCP Server
4.5/10Long-term memory for AI agents: local-first PKM with provenance and hybrid search.
Agent Search MCP
4.5/10Free-first Chinese and English web search MCP using zero-key sources and inspectable evidence.
Grounder
4.5/10Web grounding for local & cloud LLMs: search, fetch, token-capped evidence packs, and research.
Rag MCP
4.5/10Minimal RAG-over-a-corpus MCP retrieval: search_knowledge returns cited chunks. Local embeddings.
Scrapio MCP
4.5/10Fetch, crawl, and search the web: Google, Amazon, Walmart, Booking.com, Agoda, and YouTube data.
Kilonova MCP
4.5/10Persistent local knowledge for AI coding agents with structured records, search, and DOT context.
MCP Server
4.5/10Search 1,032 verified smart contract vulnerability findings from Sherlock audits by pattern.
MCP Server Malcolm
4.5/10MCP server for Malcolm (Zeek/Suricata/Arkime/OpenSearch): threat-hunting access for AI 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.