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 Eurlex
4.3/10Eurlex MCP client: Access EU law & Official Journal. https://www.lexsocket.ai/
MCP Ted
4.3/10TED MCP Server: Real-time EU public tenders access. https://www.lexsocket.ai/
Autonomous Prime
4.3/10162 AI agents for Solana crypto intelligence, wallets, and x402 micropayments.
Mangrove Trader
4.3/10Social trading leaderboard. 9 MCP tools, x402 micropayments (USDC on Base).
Competitive Intel
4.3/10SEC filings, patent data, and trade data. 4 competitive intel tools.
Cybersecurity Vuln
4.3/10CVE lookup via NIST NVD, CISA KEV, EPSS, and MITRE ATT&CK. 7 tools.
Federal Financial Intel
4.3/10SEC EDGAR, CFPB complaints, and BLS employment data. 4 tools.
Gov Contracts
4.3/10SAM.gov contracts and USAspending awards. 4 procurement tools.
Natural Disaster Intel
4.3/10FEMA disasters, NOAA weather alerts, USGS earthquakes. 4 tools.
Us Safety Recalls
4.3/10NHTSA vehicle recalls and FDA food/drug recalls. 4 tools.
Integritypulse
4.3/10Verified cloud cost forecasting for AI agents. AWS, GCP, Azure pricing matrix.
Openclaw Finops
4.3/10Verified cloud cost forecasting for AI agents. AWS, GCP, Azure pricing matrix.
Google MCP
4.3/10Streamable HTTP MCP server for Google Calendar and Sheets with OAuth login.
Meitre MCP
4.3/10MCP server for Meitre restaurant reservations.
Console MCP Server
4.3/10The official MCP Server from Mia-Platform to interact with Mia-Platform Console
Mifactory Agent Memory
4.3/10Persistent memory for AI agents across Claude, ChatGPT and any MCP client.
Noto Crm
4.3/10Minimalist CRM with AI agent for freelancers — pricing, features, comparisons
MCP Server
4.3/10Deprecated - moved to ink.ml/ink
Refund Decide
4.3/10Refund eligibility notary for US subscriptions. Returns ALLOWED/DENIED/UNKNOWN.
Tinify Ai
4.3/10MCP server for Tinify image optimization — one tool, max optimization
Bc Curriculum
4.3/10Query the full BC K-12 curriculum: Big Ideas, Competencies, Content, and more.
Proof Of Commitment
4.3/10Behavioral trust scoring: domains, GitHub repos, npm, PyPI packages.
Bstorms
4.3/10Free execution-focused playbooks. Brainstorm with other agents. Tip if helpful.
Hmr
4.3/10Hot Module Reload (HMR) for Python with reactive programming and MCP tools
Roomza
4.3/10Hotel and room intelligence from Roomza: scores, reviews, and room details.
Agent Teller
4.3/10Verify AI agent payments and detect fraud. Input: agent_id, amount, service_id.
MCP Server
4.3/10Official Sevalla MCP — full PaaS API access through just 2 tools.
Shipswift
4.3/1040+ production-ready SwiftUI recipes for building full-stack iOS apps via MCP.
Slima
4.3/10MCP Server for Slima - AI Writing IDE for Novel Authors with AI Beta Reader.
Defillama MCP
4.3/10DefiLlama MCP — TVL, yields, volumes, fees, and protocol analytics for DeFi.
Pyth Hermes MCP
4.3/10Pyth Hermes MCP — real-time price feeds and oracle data for DeFi agents.
Bart MCP
4.3/10Real-time BART departures, trip planning, fares, stations, and advisories.
Muni MCP
4.3/10Real-time SF Muni departures, routes, alerts, vehicle positions, and schedules.
Mirelia Patent Market
4.3/10AI-optimized patent data marketplace providing structured JSON datasets.
Partd MCP
4.3/10CMS Medicare Part D drug spending and prescriber data. 2024 quarterly data.
Syenite
4.3/10DeFi interface for AI agents: swap, bridge, yield, lending. Live at syenite.ai.
Trayd MCP
4.3/10Trade Robinhood through natural language in Claude Code.
Keeperhub MCP
4.3/10MCP server for KeeperHub blockchain workflow automation
Tldraw
4.3/10Draw and visually collaborate with your agents on tldraw's canvas.
Turbometrics MCP
4.3/10Website performance monitoring: scans, Core Web Vitals, RUM data and alerts.
Cissp Study Group
4.3/10CISSP exam prep: 3,600+ practice questions, study stats, and readiness scoring
Ai Compliance Monitor
4.3/10Regulatory intelligence for AI agents across jurisdictions
Vivid MCP
4.3/10Open a Vivid Business account from your AI chat via MCP.
Apibase
4.3/10327 tools, 92 providers. Pay per call via x402 + MPP. One MCP endpoint.
Governance
4.3/10Governance copilot for AI-assisted coding. 71 packs, 532 rules, proof bundles.
Mifactory Email
4.3/10Send transactional emails for AI agents via SMTP. Templates included.
Mifactory Payments
4.3/10Stripe payments for AI agents. Create links, verify, manage customers.
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.