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.
Infrawise
4.5/10Static infrastructure analysis via MCP: databases, AWS services, IaC, and code patterns.
Freshtrack
4.5/10USDA food shelf-life database, food safety, storage tips, food waste cost calculator.
Whatsapp MCP
4.5/10WhatsApp MCP. SQLCipher-encrypted, scrubber-CI-gated, draft-and-confirm sends, voice transcription.
Code Index
4.5/10Быстрый индексатор кода для AI-моделей. Rust + tree-sitter + SQLite. Мгновенный поиск по символам.
Memo
4.5/10Local MLX-native memory for AI agents — markdown-on-disk, sqlite-vec + BM25 hybrid, zero cloud.
Dokploy MCP Server
4.5/10Dokploy MCP server: manage apps, Docker Compose, databases, domains, backups, and servers.
Usda MCP Server
4.5/10Search foods, compare nutrients, and look up the full USDA FoodData Central database.
Postgres
4.3/10Connect to your PostgreSQL database to query data and schemas.
Supabase
4.3/10Connect to your Supabase database to query data and schemas.
MCP Server
4.3/10GibsonAI MCP server: manage your databases with natural language
Ink
4.3/10Deploy and manage applications, databases, domains, and git repos
Uk Vet Medicines
4.3/10UK veterinary medicines — VMD database, withdrawal periods, cascade rules
Chromadb Remote MCP
4.3/10Remote ChromaDB vector database MCP server with streamable HTTP transport
MCP Server
4.3/10MCP server for managing Prisma Postgres.
Company Lens MCP Registry
4.3/10Search Japanese company database
Pharma Regulatory
4.3/10Drug safety: DrugBank, interactions, FAERS, WHO, TGA. 7 databases. Free.
Read Only Local Mysql MCP Server
4.3/10MCP server for read-only MySQL database queries in Claude Desktop
Read Only Local Postgres MCP Server
4.3/10MCP server for read-only PostgreSQL database queries in Claude Desktop
U2 MCP
4.3/10Connect AI assistants to Rocket Universe/UniData MultiValue databases via MCP.
Airtable MCP Server
4.3/10Read and write access to Airtable database schemas, tables, and records.
Openfoodfacts MCP
4.3/10Search and contribute to the Open Food Facts database.
Genai Toolbox
4.3/10MCP Toolbox for Databases enables your agent to connect to your database.
MCP Toolbox
4.3/10MCP Toolbox for Databases enables your agent to connect to your database.
Sqlaugur
4.3/10MCP server providing AI assistants with safe, read-only SQL Server access
MCP Server
4.3/10Provision Postgres databases + webhooks from AI coding agents in one HTTP call.
Boyce
4.3/10Deterministic SQL compiler for AI agents. Your agent stops guessing SQL.
Adomcp
4.3/10Database MCP server for schema discovery, comments, and SQL queries.
Ai Erd
4.1/10AI-powered ERD design tool. Create and manage database schemas using DBML with real-time canvas.
Datamcp
4.1/10Connect AI tools to your PostgreSQL with permissions, encryption, and audit trails.
Data
4.1/10Read-only PostgreSQL, MySQL, SQL Server access via MCP — 24 dialect-aware hosted tools.
Dxtra Radio
4.1/10Radio frequency database: FM, AM, shortwave, TV, ham, weather, emergency alerts. 15+ countries.
Querybear
4.1/10Safe, read-only Postgres and MySQL access for AI agents. Audit log + column-level controls.
Dbqueryguard MCP
4.1/10Paid remote MCP for governed database query review, SQL simulation, approvals, and audits.
Sql Server MCP
4.1/10SQL Server MCP with RAG capabilities for Windows (native ODBC support)
Sql Server MCP Macos
4.1/10SQL Server MCP with RAG capabilities for macOS (Docker SQL Server support)
Memwright
4.1/10Embedded memory for AI agents with SQLite, pgvector, and Neo4j graph search.
Hypokrates
4.1/10Pharmacovigilance hypothesis generation from 15 public drug safety databases
Colabfit MCP
4.1/10An MCP server that provides access to the ColabFit database
Feed Reader
4.1/10RSS/Atom feed reader MCP server with SQLite backend
MCP Mysql Connector
4.1/10MCP server exposing MySQL database functionalities as tools
MCP Psycopg2
4.1/10MCP server exposing psycopg2 PostgreSQL database adapter functionality
MCP Redis Server
4.1/10MCP server that exposes Redis API to AI models
MCP Server Mssql
4.1/10MCP server for Microsoft SQL Server using mssql-python
MCP Sqlite3
4.1/10MCP server exposing sqlite3 library functionality
Dbatools MCP Server
4.1/10MCP server for dbatools — exposes SQL Server management commands as MCP tools
Mssql Dba
4.1/10An MCP server that provides [describe what your server does]
MCP Data Pipeline Connector
4.1/10Universal data connector for CSV, Postgres, and REST APIs via DuckDB
Dagpipe
4.1/10Crash-proof LLM pipelines. Resumes from failure without a database.
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.