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.
Reinfo
3.7/10国土交通省の不動産情報ライブラリから不動産価格データを取得するためのサービスです。
Retrochat
3.7/10Join RetroChat rooms, read context, register agents, and talk with humans.
Webclaw
3.7/10Web extraction MCP server. Scrape, crawl, extract, summarize any URL to clean markdown.
MCP Kql Server
3.7/10Execute KQL in AI prompts via NL2KQL with schema discovery and Azure Data Explorer integration
Greeting MCP Server
3.7/10An MCP server greeting
R Packagedev MCP
3.7/10MCP server for R package development using usethis, devtools, renv, and testthat
Spaceship MCP
3.7/10Manage domains, DNS records, contacts, marketplace listings, and more via the Spaceship API
Local Voice MCP
3.7/10Give your MCP clients the ability to speak by running local voice models using Chatterbox TTS
Ibmcloud
3.7/10IBM Cloud CLI MCP server
Nido
3.7/10Manage temporary or persistent Linux VMs (QEMU/KVM). Designed for AI agents and automation.
Predictive Maintenance MCP
3.7/10Industrial vibration analysis, bearing fault diagnosis, ISO 20816, and ML anomaly detection
Netlicensing MCP
3.7/10Labs64 NetLicensing MCP server for AI-driven software license lifecycle management.
Bitbucket MCP
3.7/10Model Context Protocol (MCP) server for Bitbucket Cloud and Server API integration
Smartschool MCP
3.7/10Access Smartschool courses, grades, assignments, and messages through the Model Context Protocol
Noderail
3.7/10Provenance and governance layer for AI-readable knowledge. NodeRail answers what AI should trust.
Prefect MCP Server
3.7/10MCP server for Prefect. Monitor and debug workflows, deployments, and automations.
Planform MCP
3.7/10Create and manage Planform UML diagrams, nodes, and links. For VS Code and Cursor.
Signoz MCP Server
3.7/10SigNoz MCP server: access metrics, traces, logs, alerts, and dashboards via AI assistants
Tendem MCP
3.7/10AI + Human Agent platform for getting tasks done. Create, manage, and track tasks powered by Tendem.
MCP Okx
3.7/10MCP Server for okx.com
MCP Quickstart
3.7/10quickstart for mcp deployment
Jobdonebot
3.7/10MOVED: This server has been renamed to com.jobdonebot/tools. Please use the new name.
Aidb
3.7/10Debug any supported language with breakpoints, variable/state inspection, and stepping.
Propresenter MCP
3.7/10ProPresenter 7 MCP server
Appium MCP
3.7/10MCP server for Appium mobile automation on iOS and Android devices with test creation tools.
Vynn MCP
3.7/10Self-improving AI workflows with backtesting, prompt optimization, and scheduling
Stylobridge
3.7/10Air-gapped Markdown/PDF to Word converter with brand templates and audit logging.
Agent Observability
3.7/10Agent observability: structured logging, cost tracking, and compliance audit trails
Append Log MCP
3.7/10A generic append-only log MCP server. Persist timestamped JSON entries and query them by recency.
Vettly
3.7/10Content moderation for AI applications. Moderate text, images, and video with configurable policies.
C2Pa MCP
3.7/10Read and verify Content Credentials (C2PA) from images and media using the c2pa Rust SDK
MCP Property Valuation Server
3.7/10MCP服务器，提供房产小区评级和评估功能
MCP Zmq
3.7/10MCP server for ZMQ messaging
Redshift MCP Server
3.7/10Secure, read-only access to Amazon Redshift with schema introspection and smart sampling
Percept
3.7/10Give your AI agent ears — ambient voice intelligence with 8 MCP tools for Claude Desktop
Weather MCP
3.7/10Weather forecasts, alerts, air quality, marine, radar imagery, lightning. NOAA + Open-Meteo.
Playwright MCP
3.7/10Playwright Tools for MCP
MCP Jira Server
3.7/10MCP server for self-hosted Jira instance with Personal Access Token authentication
Engineer Your Data
3.7/10MCP server for data engineering: validation, transformation, visualization, and APIs.
MCP Server
3.7/10GoReleaser MCP server
Jfrog Dummy MCP
3.7/10JFrog dummy MCP server
Bytario
3.7/1040 MCP tools for image, PDF, QR, barcode, data, text, color, and render operations.
Dead Drop Content
3.7/10Publish-ready articles on demand. Send a topic, get back SEO-optimized content with images.
Hopx MCP
3.7/10Execute code in isolated cloud containers. Supports Python, JavaScript, Bash, and Go.
Hostinger Api MCP
3.7/10MCP server for Hostinger API
Nansen MCP
3.7/10DEPRECATED - This server has been moved to io.github.nansen-ai/nansen-mcp. Do not use.
Vikunjamcp
3.7/10An MCP server that provides access to Vikunja, a self-hosted task management solution.
Korea Stock MCP
3.7/10MCP server for korea stock
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.