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.
Metabase Ai Assistant
4.1/10MCP Server for Metabase - 111 tools for SQL generation, dashboards & PostgreSQL
MCP Server
4.1/10MCP server for Florentine.ai - Natural language to MongoDB aggregations
Seo Crawler MCP
4.1/10Crawl and analyse websites for SEO errors using Crawlee with SQLite storage
Pgtuner MCP
4.1/10provides AI-powered PostgreSQL performance tuning capabilities.
Che Apple Mail MCP
4.1/10Apple Mail MCP — 44 tools, SQLite millisecond search, .emlx parser, batch ops
Memory Fts
4.1/10Long-term memory for Claude Code with SQLite FTS5 search and BM25 ranking
Mysql
4.1/10An MCP server for MySQL databases.
Oracle
4.1/10MCP server for interacting with Oracle databases
Postgres
4.1/10MCP server for interacting with PostgreSQL databases
Mimer MCP
4.1/10An MCP server with Mimer SQL Database Connectivity
Mongodb MCP Server
4.1/10MongoDB Model Context Protocol Server
MCP Server Motherduck
4.1/10SQL analytics and data engineering for AI Assistants and IDEs
MCP Neo4J Aura Manager
4.1/10MCP server for Neo4j Aura Database Instance Manager.
Db MCP
4.1/10SQLite MCP server with OAuth 2.1, HTTP/SSE, 122 tools, and smart tool filtering
Gnosis
4.1/10Zero-config MCP server for searchable documentation. SQLite or PostgreSQL.
Sqlite
4.1/10SQLite MCP — query databases, inspect schemas, explain queries, export data.
MCP Datalink
4.1/10MCP server for secure database access (PostgreSQL, MySQL, SQLite)
Databricks Sdk MCP
4.1/10263 tools for Databricks: Unity Catalog, SQL, Compute, Jobs, Serving, and more.
Database
4.1/10SQL formatting, schema visualization, migration generation
MCP Sqlite Tools
4.1/10MCP server for local SQLite database operations
Tmdb MCP Server
4.1/10MCP server for The Movie Database (TMDB) API
Vidlens MCP
4.1/10YouTube as a queryable database for AI agents. 41 tools, zero config.
MCP Trino
4.1/10MCP server for Trino distributed SQL query engine access
Db Connect MCP
4.1/10Multi-database MCP server for PostgreSQL, MySQL, and ClickHouse
Gwas MCP
4.1/10Access 30+ bioinformatics tools from 14 databases.
Hana Cli
4.1/10150+ SAP HANA database tools as MCP tools for AI assistants
Dbx
4.1/10Query databases from AI agents using connections configured in DBX.
Queryshield
4.1/10Secure SQL proxy for AI agents — NL→SQL, AST safety, per-agent RLS, audit log.
Notion
4.1/10Create, update, and manage pages, databases, and workspace users
Pinecone
4.1/10Create and manage vector database indexes, backups, and collections
Database Universal MCP
4.1/10database-universal-mcp MCP server by MEOK AI Labs
Sql Builder Ai MCP
4.1/10sql-builder-ai-mcp MCP server by MEOK AI Labs
Code Index
4.1/10SQLite-backed hybrid (vector + FTS) code search index for Claude Code over MCP.
Migraflow MCP
4.1/10AI-powered database migration. Analyze schemas, generate SQL, calculate risks.
Safedb MCP
4.1/10A secure MCP server that lets AI agents query databases safely.
Mysql MCP Server
4.1/10Python MCP server for MySQL database inspection and querying
Postgresql MCP Server
4.1/10Python MCP server for PostgreSQL database inspection and querying
Cpretzinger Ai Assistant Simple
3.9/10UPDATED 9/1/2025! NEW TOOLS! Use the Redis Stream tools with n8n MCP Client Node for use anywhere!…
MCP Server
3.9/10Kotlin compile-time SQL library. Docs, code validation, and SQLite execution tools.
Versedb MCP
3.9/10Comic book database — search comics, creators, characters, and manage your collection.
Fincontext
3.9/10Read-only bank & investment accounts via Plaid: balances, holdings, transactions, SQL analytics.
MCP Server
3.7/10Cold email, email warmup, LinkedIn outreach, and B2B lead database via MCP.
Mssql
3.7/10MCP server for Microsoft SQL Server — schema discovery, profiling, safe writes, and DDL
Mssql Reader
3.7/10Read-only MCP server for Microsoft SQL Server — schema discovery, profiling, safe querying
Node Server Orchestrator
3.7/10MCP server for orchestrating Node.js development servers (backend, frontend, databases, etc.)
MCP Server
3.7/10CloudQuery MCP server for asset inventory data. Supports CLI, PostgreSQL, and Platform modes.
Saij MCP
3.7/10Search Argentine legal databases: court decisions, legislation, summaries, doctrine
MCP Redis
3.7/10Natural language interface designed for agentic applications to manage and search data in Redis.
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.