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.
MCP Server
5.9/10Agent-native web hosting — deploy sites, manage DNS, register domains, scale infrastructure
MCP Server
4.9/10Deploy websites from AI agents. Free at mcp.shipstatic.com. Install for the full toolset.
MCP Server
4.9/10Deploy AI user personas to validate user journeys at scale. Find UX friction before real users do.
Cuongpo Coti MCP
4.7/10Connect to the COTI blockchain to manage accounts, transfer native tokens, and deploy and operate…
Cuongpo Coti MCP 1
4.7/10Manage COTI accounts, deploy private ERC20 and ERC721 contracts, and transfer tokens and NFTs with…
Willform Agent
4.7/10Deploy containers on Kubernetes with x402 billing. 9 workload types and source builds.
MCP Server
4.7/10Develop, manage, and debug Railway projects, services, and deployments from within agents.
Deploy
4.7/10Deploy any web project with one command. AI-native platform with self-healing feedback.
MCP Server
4.5/10Document hosting and encrypted agent memory with multi-tenant persistence.
Datadog
4.5/10Monitor infrastructure, manage agents and deployments, track metrics, logs, and events
Hatchbox
4.5/10MCP server for Hatchbox Rails hosting — env var inspection, deploys, and process monitoring.
Vercel
4.5/10MCP server for Vercel — manage deployments and view build and runtime application logs.
Alpic MCP
4.1/10Manage your projects, debug deployment, and check analytics for any MCP server you host with Alpic
Preflyte
4.1/10Evidence-based market data for AI agents deploying capital in DeFi. Empirical, not advertised.
Hatchable
4.1/10Build, deploy, and host full-stack web apps from any MCP client. DB, auth, storage, cron included.
Fly Io
4.1/10MCP server for managing Fly.io machines, apps, logs, and Docker images.
Deploy App
3.9/10AppDeploy turns app ideas described in AI chat into live full-stack web applications
MCP Server
3.7/10Deploy, monitor, and manage your OpenClaw AI assistants via natural language.
MCP Server
3.7/10Deploy forms and sites to live URLs from AI conversations with automatic form capture.
MCP Server
3.5/10Deploy sims to any screen. Control your displays with Claude.
MCP Server
3.5/10Deploy sims to any screen. Control your displays with Claude.
MCP Server
3.5/10Provides read access to your GKE and Kubernetes resources.
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.