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.
Fify
4.7/10Turn grounded AI answers into trusted comparisons, plans, timelines, and decision views.
Norway Location Transport MCP
4.7/10Norwegian transport (Entur) and geodata (Kartverket): trips, departures, addresses, elevation.
Dmoera Creator
4.7/10Build, backtest, and deploy crypto trading strategies via MCP with 7-stage validation.
Quorum
4.7/10Market evidence with receipts: every claim resolves to a real stored record you can fetch back.
Deliverability Doctor
4.7/10Check if a domain can be email-spoofed: SPF, DMARC, DKIM, MX graded from public DNS. Authless.
Seamgrin
4.7/10Find alterations, free tailor training, and paid work opportunities for experienced tailors.
Cerebro MCP
4.7/10Government tenders, awards and pre-tender pipelines from 21 official sources as MCP tools.
Specmcp
4.7/10Live access to gematik Telematikinfrastruktur (TI) specs and certification requirements.
Oka Anywhere
4.7/10Your office's procedures inside Claude or ChatGPT - verified citations or an honest refusal.
Seenrelay
4.7/10Cooperative freshness for AI agents. CHECK before revalidating; OBSERVE what you independently saw.
Smartfetch
4.7/10Read, fetch, scrape, and render public webpages into clean text, Markdown, links, and metadata.
Alun Alun
4.7/10Indonesian-language public square for AI agents with daily limits and a public action ledger.
Openmm MCP
4.7/10MCP server for OpenMM — exposes market data, account, trading, and strategy tools to AI agents
Carsensor Price Range MCP
4.7/10Get a used car's market-price range (min/max/median) by model and year from carsensor.net.
MCP Server
4.7/10Verifica RFCs contra las listas del SAT (69/69-B CFF, EFOS): veredicto de riesgo fiscal.
Gryz
4.7/10Publish and manage shareable Markdown/HTML docs from any AI assistant. Free with a Gryz account.
Youtube Email MCP
4.7/10Find the contact email of YouTube channels from the link, the @handle or the channel_id. Resolves th
Solucortex MCP
4.7/10Living technical memory for AI agents: recall approved project context, record what was learned.
Oneda
4.7/10Persistent, governed institutional memory for Claude Code — specs, decisions, learnings.
Agent Resolve MCP
4.7/10Escrow, verification, and settlement platform for AI agents hiring other AI agents.
Content Moderation Api
4.7/10Pay-per-call profanity/explicit-content detection for AI agents. $0.005 USDC per call, no signup.
Link Preview Api
4.7/10Pay-per-call Open Graph/link preview metadata for AI agents. $0.01 USDC per call, no signup.
Grith MCP
4.7/10GRITH MCP for persistent citizen identity, private memory, return proof, and city doors.
Protheus MCP
4.7/10TOTVS Protheus ERP for AI: stock, sales, orders, customers and MRP. Read-only, official API.
MCP Server
4.7/10Team-aware memory: intent, decisions, real-time conflicts for AI coding assistants.
Agentfolio MCP Server
4.7/10AI agent identity verification via SATP on Solana. Trust scores and on-chain attestations.
Eustore
4.7/10S3-compatible European object storage for AI agents. GDPR-compliant, EU-hosted, crypto payments.
Claude Kvm
4.7/10MCP server — control remote desktops via VNC with a native Swift daemon and Apple Vision OCR
Browser MCP
4.7/10Give AI agents control of your real, logged-in Chrome. Chrome extension + MCP server, 34 tools.
MCP Server Woocommerce
4.7/10101 tools for WooCommerce store management with field filtering and guided prompts.
Prodlint
4.7/10Production readiness for vibe-coded apps. 52 checks for security, reliability, and performance.
Air Sdk
4.7/10Collective intelligence for browser automation agents. Site capabilities, selectors, and extraction.
Containerization Assist
4.7/10TypeScript MCP server for AI-powered containerization workflows with Docker and Kubernetes support
Cloaked
4.7/10Trustless spending accounts for AI agents on Solana with on-chain enforced limits.
Scrapling
4.7/10Web scraping with stealth HTTP, real browsers, and Cloudflare bypass. CSS selectors supported.
Guesty
4.7/10Guesty property-management MCP. Read-only: reservations, listings, calendar, guests, revenue.
Deepseek
4.7/10Official DeepSeek MCP server for chat, completion, model listing, and balance endpoints.
Codebase Memory MCP
4.7/10Codebase knowledge graph for AI agents — 159 languages, sub-ms queries, 99% fewer tokens.
Threejs Devtools
4.7/10Inspect and edit Three.js scenes, materials, shaders, lights in real time from any AI agent
Projgraph
4.7/10Analyze .NET solutions: Generate Mermaid graphs, ERDs, class diagrams, and project metrics.
Q Ring
4.7/10Quantum-inspired keyring for AI coding agents with superposition, entanglement, and tunneling.
Ipgeolocation Io MCP
4.7/10Official MCP server for IP geolocation, security, ASN, abuse, timezone, astronomy, and user-agent.
Webpeel
4.7/10Fetch any web page as clean, AI-ready markdown with smart HTTP-to-browser escalation.
Agent Guardrail
4.7/10Action-level governance for AI agents -- control what they DO, not what they SAY
Report Needs
4.7/10MCP server for AI agents to report infrastructure needs they encounter during task execution
Judges
4.7/1045 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
Queue Pilot
4.7/10MCP server for RabbitMQ and Kafka message inspection with JSON Schema validation
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.