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.
Memory MCP
4.7/10SQLite-backed MCP server for persistent memory, full-text retrieval, and graph traversal.
Engram Server
4.7/10Durable memory for AI agents: fact extraction, hybrid retrieval, temporal graph. SQLite/Postgres.
Gleif MCP Server
4.7/10Access the GLEIF LEI database for company verification, KYC, and ownership research.
MCP Encrypted Sqlite
4.7/10MCP server for encrypted SQLite databases (SQLCipher 4) - Works with MoneyMoney, KeePass and more
Schemacrawler Ai
4.7/10Enables natural language schema queries — explore tables, keys, procedures, and get SQL help fast
Same
4.7/10Persistent memory for AI coding agents. Local-first SQLite + vector search. 17 MCP tools.
Sql Sentinel
4.7/10SQL Server monitoring and diagnostics for AI agents using Extended Events. No ODBC drivers required.
MCP Local Wp
4.7/10WordPress database access via Local by Flywheel. Execute read-only MySQL queries and inspect schema.
Clude
4.7/10Portable agent memory anchored on Solana. Local SQLite + vector recall, open export.
Dbmcp
4.7/10Database MCP server for MySQL, MariaDB, PostgreSQL & SQLite with PII redaction and write-prevention
MCP Mssql
4.7/10Read-only MCP for Microsoft SQL Server: metadata discovery, parameterized SELECT, plans.
Claude Webcache
4.7/10Cross-session WebFetch cache for Claude Code. Unlimited TTL by default, SQLite, MCP plugin.
Warehouse MCP
4.7/10Production MCP server for Postgres, Oracle, Snowflake, BigQuery, Redshift, DuckDB, MotherDuck.
Atlaso
4.7/10Open-source memory for AI agents. Conflict-flagging recall, scope-bag dispersion, local SQLite.
Infrawise
4.7/10Live AWS, database & Kafka infrastructure context for AI coding assistants via MCP.
MCP Tuss
4.7/10Consulta tabelas TUSS da ANS: procedimentos, medicamentos, diárias e taxas via SQLite local.
Memory Vault
4.7/10Local-first AI memory layer with hybrid search. Postgres + pgvector. Self-hosted, MIT.
Blackwall
4.7/10Pre-action risk gate: AI agents call before any irreversible action (money, SQL, delete).
Memex
4.7/10Local MCP memory for coding agents. SQLite on your machine — preferences persist across chats.
Delx Memory
4.7/10Local-first persistent memory MCP: shared SQLite key/value store, searchable, TTL-aware, secret-safe
Postgres MCP Secured
4.7/10Enterprise PostgreSQL MCP secured by Aegis Zero-Trust to block unauthorized SQL injections.
Igdb
4.7/10Video game database: search games, companies, genres, and platforms via IGDB. By UnClick.
Tribal
4.7/10Self-hosted semantic memory over MCP for an engineering team's tacit knowledge. Needs Postgres.
Stackql MCP
4.7/10SQL-native query and provisioning engine for cloud infrastructure, served over MCP.
Cli
4.7/10Deploy and monetize agent-built apps: login, database, usage billing, and end-user-pays.
Engram
4.7/10Local-first persistent memory for AI agents — SQLite + local embeddings, MCP-native, no cloud.
Sqlservermcp
4.7/10MCP server for SQL Server: schema inspection, safe read-only queries, query plan analysis
Context Bridge
4.7/10MCP memory server for AI coding assistants. Windows Service, ONNX embeddings, SQLite vector search.
Litescope
4.7/10Operations toolchain for SQLite, Cloudflare D1 & Turso: inspect, diff, migrate, monitor & repair.
Vectorcache
4.7/10x402-gated semantic vector cache for agent swarms: Redis-backed similarity lookup. Paid in USDC.
Quarry
4.7/10Safety-railed database access for agents: Postgres, MySQL, Redis. Read-only by default.
Dynoxide
4.7/10DynamoDB-compatible database engine in Rust on SQLite, with an MCP server for coding agents.
MCP Server
4.7/10Encrypted-first embedded database with vector search and agent memory, exposed as MCP tools
Sqlsure
4.7/10Semantic SQL inspector: catches double-counting, wrong joins, PII exposure before execution.
Sql
4.7/10Read-only SQL querying + schema introspection over Postgres & SQLite, with a gated write mode.
Perseus Vault
4.7/10Local-first MCP memory server: SQLite, FTS5 and vector search, AES-256-GCM. 55 tools, no cloud.
Anamnesis
4.7/10Cross-machine, file-first memory for Claude Code: markdown + SQLite FTS5, synced with git
MCP Server
4.7/10Spec-first code generation: OpenAPI, GraphQL, Protobuf, and SQL to typed clients in 11 languages.
Aifordatabase MCP
4.7/10Query any database in plain English or SQL through a guardrailed, read-only data layer.
Nvd
4.5/10NVD MCP — wraps the NIST National Vulnerability Database API (free, no auth)
Trivia
4.5/10Trivia MCP — wraps Open Trivia Database (free, no auth)
Code Sandbox
4.5/10Execute Python, JavaScript, SQL code in a sandbox. x402 micropayment.
Urlhaus
4.5/10URLhaus MCP — wraps abuse.ch URLhaus malware URL database (free, no auth)
Gdelt
4.5/10GDELT MCP — Global Database of Events, Language, and Tone (free, no auth)
Nsf Awards
4.5/10NSF Awards MCP — National Science Foundation award database (free, no auth)
Discogs
4.5/10Discogs MCP — music release / artist / label database
Malwarebazaar
4.5/10MalwareBazaar MCP — abuse.ch malware sample database (free, key required)
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.