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.
Livenxmcp
3.3/10MCP server for LiveAction LiveNX (quay.io / MCP registry test publish)
Agkit
3.3/10AgentKit management-plane CLI + MCP server (agkit).
MCP Server
3.3/10Brototype MCP Hub — Query Brocamp Data
Heterogent
3.3/10Hire AI agents with trustless USDC escrow on Solana from your AI assistant.
MCP Server
3.3/10Search your AI chat history from Claude, Cursor, Codex, and other MCP clients.
Pgtriage
3.3/10MCP server for PostgreSQL performance auditing with actionable SQL fixes.
Agents U Cash
3.3/10Non-custodial HTTP-402 crypto payments for AI agents. 77-tool MCP server.
Rtl Lint MCP
3.3/10Lint Verilog and SystemVerilog files and projects with structured diagnostics.
Keystone Verify Proxy MCP
3.3/10VM-side verify proxy for keystone attestations
Meok Article 50 Kit MCP
3.3/10EU AI Act Article 50 compliance kit — high-risk AI system readiness checker
Mcpsentry
3.3/10Security scanner and runtime proxy for MCP servers.
Topicgate
3.3/10Secure local access to MQTT topics through MCP.
Ssh Nexus
3.3/10MCP server and web terminal for shared SSH sessions and reusable command sets.
Agents U Cash
3.3/10Non-custodial HTTP-402 crypto payments for AI agents. 79-tool MCP server.
Livenxmcp
3.3/10LiveNX Network Observability MCP Server
Livewiremcp
3.3/10LiveAction LiveWire MCP Server
Carstrike MCP Server
3.3/10Live JDM auction search, SEV compliance checks, and import cost calculator.
Hypermarrow
3.3/10Local-first long-term memory for AI coding agents. Stored on your own machine.
Harmony MCP
3.3/10Repo rules enforcement for AI agents. Checks diffs against repo conventions.
Token Gate MCP
3.3/10Token and context budget for AI agents. Tracks spend and gates the session.
Kindlesms
3.3/10Send SMS, manage approved sender IDs, and check credits via KindleSMS.
Tern
3.3/10Model Context Protocol (MCP) server for Tern E2E testing platform
Integritymcp
3.3/10BlueCat Integrity MCP Server (formerly bammcp)
Lowdown Proxy
3.3/10stdio proxy and MCP tools for recording AI agent interactions.
Ubitoushiha My First MCP
3.3/10My first MCP server for testing
Test MCP Server
3.3/10Internal test MCP server for local dev and Bifrost integration testing.
Skill Maintenance MCP
3.3/10技能库维护 MCP server:损坏扫描/改前备份/决策日志/体检(skill-evolution 机械环节工具化),uvx 一行接入
Google Ads Library
3.3/10Visual MCP server for Google Ads Transparency Center. See ad copy in chat.
MCP Api
3.1/10GoMarble MCP API Server
Skybridge
3.1/10Test server
MCP Server
3.1/10Official Notion MCP server
Remote MCP Server
3.1/10Coupler.io remote MCP server
Whiteboard
3.1/10Whiteboard MCP server
Blockscholes MCP Server
3.1/10NaN - DO not use, test.
Workmagic MCP
3.1/10WorkMagic MCP
Clouddj
3.1/10cloud_dj
Email MCP
3.1/10Description of my MCP server
Email MCP
3.1/10Description of my MCP server
Email MCP
3.1/10Description of my MCP server
Email MCP
3.1/10Description of my MCP server
Gueguesser Chatgptapp
3.1/10Geography Guesser game
Linkup Company Research
3.1/10Description of my MCP server
Mcpimmo
3.1/10Description of my MCP server
Node Email MCP
3.1/10Description of my MCP server
Node MCP
3.1/10Description of my MCP server
Qa Test Cli
3.1/10Testing publish command
Send Email
3.1/10Description of my MCP server
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.