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.
Lastfm MCP
4.1/10Last.fm MCP server: scrobbles, charts, artist/album/track info and more
Gadgethumans MCP
4.1/1046 MCP tools + 300+ REST endpoints. Free tier, no API key. One-line install.
Xamlmcp
4.1/10Inspect and drive Avalonia, WPF, WinUI, and .NET MAUI apps through MCP.
Vmware Aiops
4.1/10AI-powered VMware vCenter/ESXi VM lifecycle and deployment with 31 MCP tools.
Vmware Avi
4.1/10VMware AVI (NSX ALB) load balancer plus AKO Kubernetes ops — 29 MCP tools.
Vmware Monitor
4.1/10Read-only VMware vCenter/ESXi monitoring with 27 MCP tools. Code-level safety.
Vmware Storage
4.1/10VMware vSphere storage management with 11 MCP tools: datastores, iSCSI, vSAN.
Stata MCP
4.1/10通过 pystata 驱动真实 Stata 的 MCP 服务器：数据加载/清洗/建模/诊断/图形导出，75 个工具覆盖完整计量工作流。
Weasley Deepmind
4.1/10Secure, fragment-based long-term memory for MCP-compatible AI agents.
Type Atlas
4.1/10Editor-grade TypeScript, Markdown, and JSON intelligence for coding agents.
MCP Server Tauri
4.1/10A Model Context Protocol server for use with Tauri v2 applications
Tx402
4.1/10Explain Algorand transactions, groups, batches, and account activity with x402.
MCP Reportia
4.1/10Reportia HTTP API as 66 curated MCP tools (accounting, mappings, SIIGO).
MCP Server
4.1/10Meter usage and manage usage-based billing from AI tools via the ClockNext API.
Apple Productivity MCP
4.1/10On-demand local Apple Mail, Calendar, and Reminders MCP server for macOS.
Google Jules MCP Server
4.1/10Model Context Protocol server for Google's Jules AI coding agent
Looppause
4.1/10LoopPause MCP server — pause agent execution and route human approval requests
Remote Ssh MCP
4.1/10Persistent stateful remote SSH sessions for AI agents via MCP + OpenSSH.
Ghost Inspector MCP
4.1/10Analyze, validate and safely update Ghost Inspector end-to-end browser tests
Figranium MCP
4.1/10MCP server implementation for Figranium
Inquisitor
4.1/10Hypothesis-driven problem solving for AI agents: probe, falsify, escalate.
Healthchecksio MCP
4.1/10MCP server for Healthchecks.io API
Figma MCP Server
4.1/10A local MCP server with full Figma REST API coverage.
MCP Cad Studio
4.1/10A self-contained parametric CAD studio MCP server with an interactive MCP App.
MCP Vscode
4.1/10A self-hosted VS Code workbench embedded as an interactive MCP App.
MCP Tenant Isolation
4.1/10Static analysis scanner for MCP server code and multi-tenant SaaS applications.
Hilan MCP
4.1/10Pull Hilan (Hilanet / חילן, חילנט) payslips and Form 106 into any AI assistant.
Shanghai Library Open Data MCP
4.1/10上海图书馆开放数据检索 MCP：纪年/家谱/建筑/红色事件/99 个 webapi + 搜韵诗词，支持 stdio 与 HTTP。
Canvas Api MCP
4.1/10MCP server exposing the Canvas LMS REST API (1,116 endpoints) for AI assistants
Pylos MCP
4.1/10Read-focused, prompt-injection-hardened email MCP server for any IMAP provider
Siigo Pyme MCP
4.1/10SIIGO Pyme as MCP tools: the 47 ExcelSIIGO functions, plus company discovery.
MCP Server
4.1/10Typed structured messaging for AI agents via AIPost.email with Ed25519 signing
Cortex
4.1/10Local multi-client RAG server over the Model Context Protocol.
Adobe Premiere MCP
4.1/10Control Adobe Premiere Pro video editing via ExtendScript.
Gimp MCP
4.1/10Control GIMP image editing via Python-Fu scripting from AI agents.
Screenplaywriter MCP
4.1/10Read, write, and analyze screenplays in Fountain format.
Deprecation MCP
4.1/10MCP server for cross-vendor API/SDK deprecation and breaking-change tracking
Sn MCP Server
4.1/10Multi-instance read-only MCP server for ServiceNow
Exogram
4.1/10Model Context Protocol server for the Exogram Authority Runtime.
Bot Factory
4.1/10Provision owner-confirmed isolated Telegram Managed Bot instances.
Korean Vocational Learning Map MCP
4.1/10한국 특성화고 전문교과 2022 개정 교육과정 학습 그래프 MCP 서버 (528과목·성취기준 47,625건, 공식 원문 전량 수록)
Deepseek Visionary
4.1/10DeepSeek web vision model as an MCP server with browser auto-login.
Scripthold
4.1/10Secure encoding-aware local workspace runtime for AI agents
Memtrust
4.1/10Independent, reproducible benchmark harness for agent-memory backends.
Teamspend
4.1/10Compares AI coding tool spend before and after a migration via MCP tools.
Fetchmcp
4.1/10Drop-in fetch MCP: clean Markdown from any URL, with JS rendering and anti-bot.
MCP Server Wise
4.1/10Wise (formerly TransferWise) MCP server for Model Context Protocol hosts
Mermaid Render MCP
4.1/10Renders Mermaid diagram syntax to PNG or SVG images for LLM clients
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.