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.
Mcpexplorer
4.9/10Search, vet & assemble MCP servers from your agent: verified tools, risk labels, and trust scores.
Hunchful
4.9/10Read and grow a person's falsifiable, consent-based model of how they work with AI (CMP).
Venture Diagnostic
4.9/10Venture Insights' free Concept Diagnostic, requested by an AI assistant for a founder.
Memeboat MCP
4.9/10Search 25,000+ meme templates and create shareable memes on memebo.at. Free, anonymous, no API key.
Noaa Tides And Currents MCP
4.9/10NOAA tides and currents: water levels, tide predictions, currents, met data, flooding, sun and moon
Cleanor
4.9/10Zero-auth MCP: image optimize, cited storage/format data, and dev utilities LLMs get wrong.
MCP Server
4.9/10Live global intelligence: real-time markets, conflicts, country risk, chokepoints, energy. 39 tools.
Japan Data Api
4.9/10Deep, obscure Japanese station, accessibility & hazard data for AI agents. English-first.
Agent Ready Kit
4.9/10Free 18-check agent-readiness scanner, robots.txt + llms.txt generator, managed agent enablement.
Price Api
4.9/10Solana DeFi MCP: Meteora DLMM brief+detail; Solana DEX scout. Commerce optional.
Justonce Memory
4.9/10Persistent, portable, bitemporal memory layer — recalled proactively across your AI tools.
Token Intel
4.9/10Solana token due-diligence: 3-source fused risk verdict incl. LP-lock depth. $0.01 via x402.
X402 Solana
4.9/10x402 paid API tools for AI agents on Solana: crypto safety, market data, KYB/AML verification.
Proxykey
4.9/10Issue, rotate and revoke scoped API-key passes for 25+ providers — the agent never sees a real key
Solar Home Incentives
4.9/10Free solar & home energy tools: estimates, incentives by ZIP, scores, cited guides, routing.
Pulsenetwork
4.9/10825 paid intelligence endpoints in one MCP server — agents pay per query via x402 USDC on Base.
Flights
4.9/10whentofly: flight search for AI agents — cheapest flexible-date round-trips + buy/wait verdict
Leaseiq Pro
4.9/10Exact lease finance calculations: equipment structuring, solvers, amortization, auto lease & loan
Linkedin MCP
4.9/10No-auth discovery endpoint for Apex by LeadShark — governed LinkedIn hands for AI agents.
Whycant
4.9/10Roast any AI agent idea from your IDE: verdict tier, readiness score, top risk, shareable URL.
Waitloop
4.9/10Agent-first waitlists: hosted signup pages with referral ranking. One tool call returns a live page.
Domani
4.9/10Internet identity for AI agents: register or broker domains, email, DNS - pay by card or USDC.
MCP Server
4.9/10The grounded data layer for any LLM: governed SQL, metrics, lineage and catalog over your data.
MCP Server
4.9/10Run 100+ AI models — image, video, audio, 3D — through one API with pay-per-use billing.
Govauctions
4.9/10US government-surplus auction search, sold-price comps, and Flip Score resale signals.
MCP Server
4.9/10Cited, receipt-backed US home-buying data & calculators — education-only, every number sourced.
Githits
4.9/10Search public open-source code, documentation, metadata, vulnerabilities, changelogs, and examples.
Openhouse Copilot
4.9/10AI open-house assistant for agents: sign-in kiosk + automated, consent-aware follow-ups.
Quant
4.9/10Prediction-market quant tools for AI agents: EV, Kelly, arbitrage, edge for Kalshi & Polymarket.
Llmpulse MCP
4.9/10AI visibility analytics for brand mentions, citations, sentiment, and GEO reports
Tradetime MCP
4.9/10Read-only trading hours for 30 stock exchanges — open now, next open, holidays, sessions.
Mediora MCP
4.9/10Doctor-reviewed blood-test markers, conditions & symptoms as agent tools. EN/RU/HE. Hosted.
Marmo Ui
4.9/10Live React design-system APIs, patterns, and code validation so AI agents build real UI, not slop.
Qscreener
4.9/10Screen and score stocks with the Quality Screener engine: filters, custom scores, and history.
Fact Check
4.9/10Fact-check claims against independent sources — fast verdict or deep multi-step investigation.
Netid
4.9/10Gives AI agents a public IPv6 identity, hostname, port forwarding, web fetch, team mesh. Free tier.
Cobbles
4.9/10The shared task board for teams and their AI agents — connect over OAuth, every action signed.
Twiceshy
4.9/10Experience memory for coding agents: validated traps, fixes and dead-ends at decision time.
Blackwall X402 Guardrail
4.9/10Pre-signature x402 payment verdict (GO/HOLD/STOP) for AI agents, with a verifiable signed receipt.
Clarity
4.9/10Condition-aware ingredient & product safety for AI agents: verdict, evidence tier, citations.
Radar
4.9/10FDA & NHTSA regulatory risk for agents: compliance, 510(k) evidence, postmarket, reimbursement.
Loppee
4.9/10Agent-first US business trust registry with neutral Trust Cards and local search.
Octoparse MCP
4.9/10Official Octoparse MCP server for template discovery, cloud tasks, and structured data export.
Registry
4.9/10Search, inspect, pull and publish reusable AI-agent harnesses from onlyharness.com.
Scribe
4.9/10Manage Scribe email signatures: templates, teammates, smart fields and campaigns, via OAuth.
MCP Server
4.9/10Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
Sports Data
4.9/10NFL/NBA/MLB/NHL/PGA + DFS and prediction-market data. Browse free; query with a free API key.
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.