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.
Update Hijack Poc
4.1/10PoC benign MCP server for update-hijack security research
Claude Memory Manager
4.1/10Cross-session memory for Claude Code — context capture, semantic search, recall
Omophub MCP
4.1/10Search, lookup, map, and navigate OMOP medical vocabularies via AI agents
Job Search
4.1/10Search Korean job postings from JobKorea and Saramin by company name
Shippost MCP
4.1/10Twitter/X tools for AI agents — read timelines, post tweets, search, and engage
Search Papers
4.1/10An MCP server to search papers from arXiv
Tavily MCP
4.1/10MCP server for advanced web search using Tavily API.
Tavily MCP Server
4.1/10FastMCP server for Tavily search API with web search and content extraction
Indiamart MCP Server
4.1/10Claude AI for IndiaMART leads - fetch, search, sync and track pipeline.
Academic Research MCP Server
4.1/10Search arXiv, Google Scholar, and Wikipedia for academic papers and knowledge
Hr Compensation MCP Server
4.1/10Search H1B visa salaries, salary benchmarks, and job market data
Legal MCP Server
4.1/10Search court records, patents, and trademarks for legal research
Real Estate MCP Server
4.1/10Search properties via Redfin and Google Maps real estate data
Redfin MCP Server
4.1/10Search Redfin properties, get property details, and market statistics
Memory
4.1/10Persistent memory for AI assistants. Store, search, and recall across sessions.
MCP Hackernews
4.1/10MCP server exposing a simple Hacker News search tool (top stories).
Image Resolver
4.1/10MCP server for context-aware royalty-free image search from Pexels and Unsplash
Ifg Tax
4.1/10International tax research — 213 jurisdictions, 500K+ legal documents.
Clirank
4.1/10Search, compare, and get docs for 210+ APIs ranked by CLI and agent relevance.
MCP Webgate
4.1/10Web search that doesn't wreck your AI's memory.
Atlassian Dc MCP Jira
4.1/10MCP server for Atlassian Jira Data Center - search, view, and create issues
Cognos Session Memory
4.1/10CognOS trust scoring (C=p·(1-Ue-Ua)) and session trace storage as MCP tools.
Video Editing MCP
4.1/10MCP Server for Video Jungle - Analyze, Search, Generate, and Edit Videos
MCP Server Search
4.1/10MCP server for web search operations
Messages
4.1/10Fuzzy search and browse Apple Messages/iMessage from CLI or MCP server
Remembrallmcp
4.1/10Persistent knowledge memory for AI agents. Hybrid search, code graph, pgvector.
Originselect MCP Server
4.1/10Search ethical, origin-verified products and brands by country of origin
Jobseek
4.1/10Search jobs, companies, and watchlists on Job Seek (jseek.co)
Elasticsearch MCP Server
4.1/10MCP server for interacting with Elasticsearch
Gemini
4.1/10MCP server for Google Gemini AI - text, image, video, research, and more
Mediawiki
4.1/10Secure MCP server for MediaWiki wikis — search, pages, categories, and more
Imessage Max
4.1/10AI-optimized MCP server for iMessage on macOS. Read, search, and send messages.
Gsearch
4.1/10Free Google Search with inline citations for any MCP-compatible AI tool.
MCP Exa
4.1/10MCP server exposing Exa websearch API
MCP External Memory
4.1/10An MCP server that gives LLMs persistent, searchable semantic memory
Dingdawg Legal Agent
4.1/10AI contract review, clause drafting, compliance checklists & legal research.
Dingdawg Sales Agent
4.1/10AI prospect research, outreach drafting, lead scoring & pipeline tracking.
Auto Skill Loader
4.1/10Auto-loads skills into agent sessions. MiniMax vision and search proxy.
Ai Dictionary MCP
4.1/10Look up, search, cite, discuss, and track AI phenomenology terms
Cowork History
4.1/10Hybrid search for Cowork history: FTS, Spotlight, and semantic vectors
Faculti
4.1/10Search academic expert insights, papers and contributions from Faculti
Croissant
4.1/10Search and book coworking spaces and conference rooms via Croissant.
Cli
4.1/10MCP package manager with trust scoring. Search, install, and audit MCP servers.
Onepiece Oracle
4.1/10One Piece TCG MCP server with card search, deck analysis, and set browsing
Ailist MCP
4.1/10MCP server for AiList — search and discover Ai projects from Claude Code
Geo Analyzer
4.1/10AI search optimization analysis with actionable findings and gap analysis
Huoshui File Search
4.1/10An MCP server that provides fast Spotlight file search capabilities for macOS
Apple Mail MCP
4.1/10Fast MCP server for Apple Mail with batch JXA and FTS5 search index.
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.