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.
Release Report Label Workbench
3.5/10Publish a stakeholder report entry
Report Style Guidance Identifier
3.5/10Set the style guidance for an executive report
Report Style Guidance Workbench
3.5/10Format a status report for stakeholders
Routing Contact Identifier
3.5/10Select a contact for a client brief
Routing Contact Workbench
3.5/10Log a client communication recipient
Support Followup Marker Identifier
3.5/10Digest a support intake marker
Task Priority Guidance Identifier
3.5/10Plan capacity handling for a task
Workspace Activity Reference Identifier
3.5/10Find the reference marker for a knowledge item
Workspace Activity Reference Workbench
3.5/10Append an operations activity entry
Workspace Note Path Identifier
3.5/10Plan a knowledge-base placement path
Workspace Note Path Workbench
3.5/10Queue a workspace publication path
Fivecoins Validation Plan
3.5/10No-signup validation planner MCP for tiny paid offers.
Oasdiff
3.5/10Detect breaking changes, generate changelogs, diff, and validate OpenAPI specs.
Baseframelabs Catalogue
3.5/10Agent-native catalogue of Baseframe Labs dev tools and MCP servers.
Composio Test
3.5/10Deprecated proof-of-concept listing. Use the official Composio server instead.
Tokkyo Maru
3.5/10特許まる — 発明を入れるだけで特許性の事前診断・明細書骨子・新規性喪失(特許法30条)判定。本人/弁理士の出願支援(代理しない)。
Vedavisor Vedic Astrology MCP
3.5/10Professional Vedic astrology tools for AI agents via MCP.
Freebeat MCP
3.5/10Freebeat MCP server for AI music videos, effects, and media uploads.
Shabaaspay Payto
3.5/10ShaBaasPay MCP server for PayTo agreements and payment initiation in Australia.
Marketing Content Production
3.5/10Brand-safe ad, email, product description, and social content production.
Dwai Ide Bridge
3.5/10AI Agent 与 JetBrains IDE 的桥接工具：获取光标代码上下文、诊断运行报错、执行脚本、推送 Diff 修改供开发者审批。
Ya Yandex Wiki MCP
3.3/10Yet Another Yandex Wiki MCP Server.
Asgcard MCP Server
3.3/10Give AI agents autonomous virtual card management via x402 and Stellar USDC
Security Controls
3.3/101,451 security controls across 261 frameworks with bidirectional mapping
Airbrake MCP Server
3.3/10Query Airbrake errors, notices, deploys, and project stats from MCP clients
Cse MCP
3.3/10MCP server for Colombo Stock Exchange data
Ninjaone
3.3/10MCP server for NinjaONE RMM with device management, monitoring, and automation
I18N Agent Action
3.3/10An i18n github action for language translate
Scrimba Teaching
3.3/10Interactive programming teacher using Scrimba's methodology for 10x retention
Remote Terminal
3.3/10Complete SSH terminal for Linux with AI/user control and dual-stream visibility
Agentgraph Trust
3.3/10Security scanning and trust verification for AI agent tools.
Yandex Tracker MCP
3.3/10MCP server for Yandex Tracker API.
Weather MCP
3.3/10A simple MCP server for getting weather information.
Agentshield
3.3/10Smart contract security for AI agents — verify, monitor, freeze, x402 payments
MCP Watchdog
3.3/10MCP security proxy - detects and blocks 40+ MCP attack classes. Zero config.
Swiftkanban
3.3/10Manage SwiftKanban boards and cards from Claude AI
Time MCP Nuget
3.3/10Get the current UTC time in RFC 3339 format.
Gearlynx
3.3/10MCP server for Gearlynx Atari Lynx emulator
Sample MCP Server Python Package
3.3/10A sample MCP server for testing
MCP Sse Demo 02
3.3/10Spring Boot MCP 服务器（示例占位描述），通过 GHCR 以 OCI 镜像发布至 MCP Registry。
Sling Cli
3.3/10Sling CLI MCP server for data pipeline and replication management
Ghost MCP Server
3.3/10Minimal MCP server for Ghost Security API - compatible with all MCP clients
Passage Protocol
3.3/10Departure and admission records for AI agents with Ed25519/P-256 signatures.
Keycloak MCP.Test
3.3/10This is just a test publish, delete me
Orchestro
3.3/10Your AI Development Conductor - 60 MCP tools for intelligent task orchestration
Llng MCP
3.3/10Manage LemonLDAP::NG SSO instances: configuration, sessions, OIDC, SAML, 2FA.
Agent Guardrails
3.3/10Merge gates and safety checks for AI coding agents via MCP.
Powerbi Analyst MCP
3.3/10Browse Power BI workspaces, run DAX queries, and page through large results.
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.