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.
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
Agent Release Auditor
4.1/10Deterministic release gate for AI-written code and coding agents.
Agentdomain MCP
4.1/10Register and manage internet domains for AI agents via AgentDomain
MCP Kinetic Gain
4.1/1075-tool MCP server for 12 Kinetic Gain specs and DefenseTech checks.
MCP Ast Explorer
4.1/10Python symbol exploration for codebase onboarding agents.
MCP Repo Mapper
4.1/10Deterministic repository structure mapping for onboarding agents.
MCP Test Runner
4.1/10Local test execution and coverage summaries for onboarding agents.
Agentsafe
4.1/10Real-time URL trust scoring for AI agents. Blocks phishing and malicious sites.
MCP Fraudlabspro
4.1/10Fraud Prevention MCP server using FraudLabs Pro API.
MCP Ip2Whois
4.1/10WHOIS domain MCP server that query the WHOIS information using IP2WHOIS API.
Magento Cloud
4.1/10MCP server for Adobe Commerce Cloud — REST API + SSH, no PHP CLI required
Gnomon MCP
4.1/10Deterministic batch tools so LLM agents stop guessing dates and math.
Outline MCP
4.1/10Tree-structured knowledge base as an MCP server
Iflow Search
4.1/10MCP server for iFlow Search web search, image search, and URL fetch tools.
Amnesic
4.1/10Persistent semantic memory for SQL databases. Postgres, MySQL, MSSQL, SQLite.
Easyeda Pro MCP
4.1/10MCP server and EasyEDA Pro extension bridge for live project assistance.
Nutriref
4.1/10Pay-per-call USDA nutrition for AI agents (x402 micropayments in USDC on Base).
Dreamwork
4.1/10AI job search agent — browse listings, generate packs, auto-apply
Presence MCP
4.1/10Read-only MCP access to presence: living project model and outcome telemetry.
Eos MCP
4.1/10MCP server for Arista EOS device operations via eAPI
Claude Code Bridge
4.1/10Durable local-first MCP relay for independent coding agents.
Caldav MCP
4.1/10CalDAV calendar operations (list, create, update, delete events) as MCP tools.
Kubeleash
4.1/10Kubernetes MCP server with RBAC-style, context-scoped guardrails for AI agents.
Toggl MCP
4.1/10MCP server for Toggl Track — gives Claude access to your time tracking data
Taskchampion MCP
4.1/10MCP server for Taskwarrior 3.x, TaskChampion, and Timewarrior task management.
Workflows MCP Server
4.1/10Store, query, and create YAML workflow playbooks for LLM agents.
MCP Server
4.1/10Cities: Skylines II wiki, encyclopedia, and mod workflow tools for AI agents.
Collective Memory
4.1/10MCP server for persistent, semantic memory across AI sessions
Clarik MCP Server
4.1/10Clarity and memory persistent workspace context manager for Claude.
Grpc Invoke MCP
4.1/10MCP server for describing and invoking gRPC methods
MCP Email
4.1/10Email for AI agents — read inbox (IMAP), search, and send (SMTP).
Localgym MCP Server
4.1/10Read-only MCP server for UK gym search using the LocalGym Agent API.
MCP Gateway
4.1/10AuthzX MCP Gateway — policy-enforcing proxy between AI agents and MCP servers
Skylight MCP
4.1/10Skylight Calendar for Claude — family events, chores, and rewards.
Thealgorithms MCP
4.1/10Search TheAlgorithms across 24 languages; fetch implementations with examples.
Mcpwp
4.1/10MCP for WordPress — connect Claude, Cursor, or Windsurf to any WordPress site.
Mac Calendar MCP
4.1/10Read-only Mac Calendar MCP server with indexed archive search.
Mac Mail MCP
4.1/10Mac Mail MCP server with full-coverage FTS5 body search for local Apple Mail.
Dns Cache
4.1/10DNS/WHOIS/SSL/geo-IP cache MCP server for AI agents.
License Checker
4.1/10OSS license metadata + compatibility checker MCP server.
Package Meta
4.1/10npm/PyPI/Cargo package metadata + downloads + maintainer health.
Regulatory Deadline
4.1/10FinCEN/SEC/EU AI Act/GDPR deadline tracker for AI agents.
Claude Wrap MCP
4.1/10MCP server that spawns and drives Claude Code sessions via claude-wrap.
Parecode
4.1/10Token-aware ripgrep code search and atomic multi-file edits for coding agents.
MCP Server
4.1/10MCP server for AKKA Finance DEX aggregator — swap quotes, routes, and execution
Orm MCP
4.1/10MCP server for @mostajs/orm: generate, lint (24 rules) & migrate EntitySchemas.
Zapi MCP
4.1/10MCP server for the Zabbix API — daily brief, problems, hosts, items
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.