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.
Interactive Terminal
4.5/10MCP server for real interactive terminal sessions — REPLs, SSH, databases, Docker
Mosta Net
4.5/101 MCP server, 13 databases, zero config. Multi-protocol transport with Auth + RBAC.
Fasttransfer MCP
4.5/10MCP server for FastTransfer — high-performance parallel data transfer between databases
Lakexpress MCP
4.5/10MCP server for LakeXpress — automated database-to-cloud data pipeline as Parquet
Migratorxpress MCP
4.5/10MCP server for MigratorXpress — cross-platform database migration with parallel transfer
Aifp
4.5/10Database-driven FP enforcement and project management for AI-maintained codebases
Fastmcp Sqltools
4.5/10A MCP server provides SQL database access with support for PostgreSQL, MySQL, and SQLite.
Refcheck
4.5/10Verify academic citations against real databases. Catches hallucinated references, exports BibTeX.
MCP Superset
4.5/10Apache Superset MCP server — 135+ tools for dashboards, charts, datasets, SQL Lab, and security
Mongo Scout MCP
4.5/10Scout your MongoDB databases with AI - safety features, live monitoring, and data quality
Postgres Scout MCP
4.5/10Scout your PostgreSQL databases with AI - safety features, monitoring, and data quality
Dbhub
4.5/10Minimal, token-efficient Database MCP Server for PostgreSQL, MySQL, SQL Server, SQLite, MariaDB
Database MCP
4.5/10MCP server for database connectivity. Multi-DB (PostgreSQL, MySQL, SQLite), 19 tools.
Database Admin
4.5/10Database admin MCP: schema inspection, query optimization for PostgreSQL and MySQL
Mockhero
4.5/10Generate realistic relational test data. 156 field types, 22 locales, JSON/CSV/SQL.
Simpliq Server
4.5/10Simpliq Data Proxy MCP Server - Connects LLMs to SQL Databases via Semantic Mapping
Chart Canvas
4.5/10Create interactive visualizations and query data sources (SQLite, CSV, Parquet, JSON)
Poly Db MCP
4.5/10Unified MCP for 20 databases: SurrealDB, ArangoDB, Virtuoso, CouchDB, Cassandra, and more
Postgres
4.5/10PostgreSQL MCP Server — 27 tools for queries, schema, CRUD, DBA, HA & server management
MCP Server
4.5/10Real-time Kubernetes network traffic visibility and API analysis for HTTP, gRPC, Redis, Kafka, DNS.
MCP Manticore
4.5/10MCP server for Manticore Search — lets AI assistants query and manage search databases.
Migrationpilot
4.5/1083 rules to catch dangerous PostgreSQL migrations before production. Lock analysis + auto-fix.
Terminal MCP
4.5/10MCP server for interactive terminal sessions — SSH, REPLs, database CLIs, TUI apps
MCP Neo4J Cypher
4.5/10A simple Neo4j MCP server that allows you to run Cypher queries against a Neo4j database.
Mysql MCP
4.5/10Enterprise-grade MySQL MCP Server with OAuth 2.0, 106 tools, and Docker deployment
Postgres MCP
4.5/10PostgreSQL MCP server with 203 tools, connection pooling, HTTP/SSE, OAuth 2.1, and tool filtering
Postgres MCP Server
4.5/10Enterprise PostgreSQL MCP server with 63 tools, 10 resources, 10 prompts for AI-native operations
Sqlite MCP Server
4.5/10SQLite MCP server with 73 tools for JSONB, full-text search, geospatial, and analytics.
Mnemon MCP
4.5/10Persistent layered memory for AI agents. SQLite FTS5, fact versioning, zero-cloud.
Local Faiss MCP
4.5/10Local FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.
MCP Debug Recorder
4.5/10Record debug sessions, commands, failed attempts, and successful fixes in local SQLite storage.
Agentmem
4.5/10Lightweight persistent memory for AI agents. Hybrid search. 16 tools. One SQLite file.
Postgres MCP
4.5/10Enterprise PostgreSQL MCP server with NL queries, hybrid search (pgvector+BM25), and web UI
Orionbelt Analytics
4.5/10Ontology-based MCP server for database schema analysis and RDF/OWL ontology generation
Orionbelt Semantic Layer
4.5/10API-first semantic layer MCP server compiling YAML models into dialect-specific SQL
MCP Sqlite
4.5/10MCP server for SQLCipher 4 encrypted SQLite databases with full CRUD operations and query support
Berth
4.5/10Database management — query, schema inspection, migrations for PostgreSQL, MySQL, SQLite.
Redash MCP
4.5/10Connect Redash to Claude -- query data, manage dashboards, and run SQL with natural language.
Saga MCP
4.5/10Jira-like project tracker for AI agents with SQLite, full task hierarchy, and dashboard
Db
4.5/10Database MCP server for MySQL, PostgreSQL, MongoDB, and SQLite with SSH tunneling support.
Tiger Cli
4.5/10Provides programmatic access to Tiger Cloud services, databases, and documentation.
Mindpm
4.5/10Persistent project memory for LLMs via SQLite. Never re-explain your project again.
W8S Astro MCP
4.5/10Natal charts, transits, history, ingress forecasting, aspects, composite & Davison charts — SQLite.
Team Memory
4.5/10Team experience database - let AI accumulate, retrieve and apply team knowledge across chats.
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
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.