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.
Olostep MCP Server
3.7/10Search, scrape, and crawl the web for AI agents. Batch scraping and answers with citations.
Qweather MCP
3.7/10a qweather mcp server
Pmat Agent
3.7/10Zero-config AI context generation and code quality toolkit with Claude Code Agent Mode support
Rash
3.7/10Transpile Rust code to POSIX-compliant shell scripts with formal correctness guarantees
Semanticapi
3.7/10Search and discover any API using natural language. 163+ providers with auto-discovery.
In Memoria
3.7/10Persistent codebase intelligence that gives AI assistants memory across sessions
Agenthub
3.7/10Enables coding agents to coordinate edits, reviews, and escalations without file locking conflicts
Selenium MCP
3.7/10Selenium Tools for MCP
MCP Redis
3.7/10Natural language interface designed for agentic applications to manage and search data in Redis.
Tool Filter MCP
3.7/10MCP proxy server that filters tools from upstream MCP servers via regex-based deny list
Local Skills MCP
3.7/10Universal MCP server for local filesystem skills with lazy loading and context-efficient discovery
MCP Ordali Memory
3.7/10MCP server for Ordali memory: SQLite-backed project memory and governance traces.
Egnyte Ai Samples
3.7/10Secure integration between AI tools and Egnyte content with search, analysis, and workflow tools.
Stellar Memory
3.7/10Persistent AI memory using orbital mechanics. 100% local, zero API keys, MCP-native.
Memorymesh
3.7/10Persistent, zero-dependency AI memory using SQLite. Local-first, cross-tool portable.
Model Radar
3.7/10Ping 134+ free coding LLMs across 17 providers, rank by latency, pick the fastest.
Srclight
3.7/10Deep code indexing for AI agents. FTS5 + embeddings + call graphs + git intelligence. Fully local.
Scrimba Teaching MCP
3.7/10Unified MCP for Scrimba's interactive programming education with visual learning
Hive MCP
3.7/10Microblogging social network for AI agents. Post, reply, boost, follow, and discover.
MCP Server
3.7/10Android mobile automation with uiautomator2. AI bot for taps, swipes, apps, XPath testing, RPA.
Workspace MCP
3.7/10Google Workspace MCP server for Gmail, Drive, Calendar, Docs, Sheets, Slides, Forms, Tasks, Chat.
Datagraph
3.7/10Urban intelligence knowledge graph. Structured locality data for civic problem-solving.
Testdino MCP
3.7/10A MCP server for TestDino
Charts MCP
3.7/10MCP server for generating charts using AntV. Supports various chart types through MCP tools.
Sampledotnetmcpserver
3.7/10Sample .NET MCP Server
MCP Defender
3.7/10Execute KQL queries against Microsoft Defender Advanced Hunting via natural language.
MCP Msdefenderkql
3.7/10Execute KQL queries against Microsoft Defender Advanced Hunting via natural language.
Agentrace
3.7/10Structured observability for AI agents. Trace steps, decisions, and errors. MCP server + CLI viewer.
Book Metadata MCP
3.7/10Search Google Books and Open Library for book metadata, covers, and publication info.
Dealhub Admin
3.7/10DealHub MCP server for admins. Manage versions and users with 7 tools via Claude AI agents.
Nexo
3.7/10Cognitive memory for AI agents. Atkinson-Shiffrin, RAG, knowledge graph. 100+ tools.
Mtg MCP
3.7/10Comprehensive Magic: The Gathering info with rules, cards, combos, and Commander deck generation
Fo Semantic MCP
3.7/10Semantic search over 50,000+ Dynamics 365 F&O artifacts: tables, forms, classes, and more.
Greeting
3.7/10MCP server providing personalized greetings with AI-powered tools using Spring Boot and Spring AI
Terraform Ingest
3.7/10Ingest and analyze Terraform modules from multiple repositories for AI RAG systems
Tangled MCP
3.7/10MCP server for Tangled git platform. Manage repositories, branches, and issues on tangled.org.
Sling Cli
3.7/10Sling CLI MCP server for querying any database, running data pipelines and managing replications
In Memoria
3.7/10Persistent codebase intelligence that gives AI assistants memory across sessions
Speed Test
3.7/10Official SpeedOf.Me server - Accurate speed tests via 129 global edge servers with analytics.
Context MCP
3.7/10Situational awareness — holidays, business hours, and platform status for timing-sensitive actions.
Norm MCP
3.7/10Statistical baselines — check if values are normal or anomalous for a given category.
Undo MCP
3.7/10Reversibility intelligence — check if actions can be undone before executing them.
MCP Server
3.7/10Deploy forms and sites to live URLs from AI conversations with automatic form capture.
MCP Server
3.7/10AI-powered meeting scheduling with intelligent auto-scheduling for Claude and AI agents.
MCP Bind Erp
3.7/10Bind ERP — Mexican cloud ERP
Konid
3.7/10Three translation options per phrase, casual to formal, with register context and audio.
Godavaii MCP Server
3.7/10GoDavaii Health AI — Indian medicine DB, drug interactions, pregnancy safety, dosage checks
Smart Speaker MCP
3.7/10Control Google Home and Amazon Alexa speakers from Claude Desktop using natural language.
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.