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.
Replicate
4.1/10Run AI models, create deployments, and manage predictions via cloud API
Apify
4.1/10Build, deploy, and run web scraping and automation actors in the cloud
Gcs
4.1/10MCP server for Google Cloud Storage with fine-grained tool access control.
Agentdomain MCP
4.1/10Register and manage internet domains for AI agents via AgentDomain
Registry
3.9/10Sovereign AI agent platform. 19 tools: discovery, transfers, staking, governance. A2A v1.0.
MCP Server
3.9/10Cloudflare MCP servers
Server
3.9/10Devopness MCP server for DevOps happiness! Empower AI Agents to deploy apps and infra, to any cloud.
MCP Server
3.9/10Generate and run high performance queries on open and private spatial data at-scale in the cloud
Acc MCP
3.9/10Autodesk Construction Cloud via APS — projects, issues, RFIs, documents, submittals.
MCP Server
3.9/10AI phone answering tools for service businesses — ROI, missed calls, demos across 18 industries
MCP Server
3.9/10Interact with your Google Cloud Composer resources using natural language commands.
MCP Server
3.9/10Interact with your Google Cloud Datastream resources using natural language commands.
MCP Server
3.9/10Interact with your Google Cloud Firestore resources using natural language commands.
MCP Server
3.9/10Real-time polls, surveys, quizzes, trivia, Q&A, and word clouds for teams, educators, and creators.
Synlake
3.9/10Unified API to query AWS, GCP, Azure and generate Terraform/CLI execution kits for AI agents.
Backlog Forge
3.9/10Crie épicos, features, histórias e tasks no Azure DevOps a partir de uma conversa.
MCP Server
3.9/10Shared Timill Cloud server: query and edit your work-platform data with full per-user RBAC.
MCP Server
3.9/10Your hosted Timill instance: query and edit your work-platform data with full per-user RBAC.
Cdata Connect Ai
3.9/10Cloud-hosted MCP server for secure AI access to enterprise data sources via CData Connect AI.
Prince
3.7/10Convert Markdown, HTML, and web pages to high-quality PDF with Prince.
MCP Server
3.7/10Cloud-hosted MCP server for Epidemic Sound
Remote Camera
3.7/10Capture photos remotely from mobile devices via S3-backed upload URLs
Aws Pricing Calculator
3.7/10Create AWS cost estimates and shareable AWS Pricing Calculator URLs.
MCP Server
3.7/10Manage CloudPepper servers, Odoo instances, backups, and deployments over MCP.
MCP Server
3.7/10A-share HS300 phase signals via Landau-Ginzburg framework. No auth required.
MCP Server
3.7/10Lowers your AWS bill by helping you clean up and optimize your setup
Okahu
3.5/10Cloud hosted Okahu MCP server that helps you manage genAI trace data
MCP Server
3.5/10Deploy applications to Cloud Run
Jumpcloud Genai
3.5/10An MCP server that provides an API to LLMs to manage their JumpCloud resources.
Api
3.5/10Official MCP server for managing OVHcloud infrastructures, services & account
Zhiji Signal
3.5/10Market phase transition signals for HS300 and BTC via MCP
Agent Web Actions
3.5/10Stealth web automation for AI agents. Login, signup, navigate, screenshot.
Ai Video Generator
3.5/10AI video generation API with x402 USDC payment. TTS voiceover, animated text.
Agent Web Actions
3.5/10Stealth web automation for AI agents. Login, signup, navigate, screenshot.
Server
3.5/10AI-powered Amazon ECS workload management
Server
3.5/10AI-powered Amazon EKS cluster management and troubleshooting
Historian MCP Server
3.3/10MCP server for querying Factry Historian.
Clouddj
3.1/10cloud_dj
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.