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.
Lmgram
4.1/10Consent-based human matchmaking for peer advice, collaboration, and practical help.
Craft
4.1/10Illumora Craft — evidence-augmented prompt compile for agents via remote MCP (OAuth) or local stdio.
Lain
4.1/10Cryptographically anchored evidence for agents: verified run receipts, proof-gated settlement.
Structa
4.1/10An AI-native context platform that accumulates an organization's judgment. Built by South Gate Inc.
Deepgent
4.1/10Company analytics for Deepgent workspaces: usage, conversations, quality, billing, KB status.
Legislacao Portuguesa
4.1/10Search Portuguese consolidated legislation: the exact in-force article, official source.
Royaltea
4.1/10Manage your RoyalTea game studio: tasks, milestones, team, and royalty data. 77 tools, OAuth 2.1.
Royaltea Public
4.1/10Free no-auth game-dev tools: revenue splits with real store cuts, agreement drafts, studio setup.
Scanner
4.1/10Stock market signals for agents: regime verdict, ranked buy list, scored stock and sector reads.
Bassethound
4.1/10Company intelligence for AI agents: a five-layer domain dossier in one sniff_domain call.
Status
4.1/10Live status and health checks for AI coding providers: Claude, Cursor, Copilot, Codex and more.
Case Law
4.1/10Search Brazilian case law from federal and state courts with verified decisions and source links.
Llamanotes
4.1/10Lucky AI study buddy over your own LlamaNotes courses: chat, progress, and AI course generation.
Au Hot Water Payback
4.1/10Heat pump vs gas hot water (AU): rebate stack, net outlay and payback verdict by postcode.
Company Brain
4.1/10Governed company memory: search decisions, rules and client facts; propose updates for review.
Zencap
4.1/10Institutional financial data with SEC filing citations, for every AI agent. OAuth 2.1.
Catalogue
4.1/10Search evidence-backed AI-tool reviews, rankings, use cases, comparisons & toolkits (read-only).
Tenant
4.1/10Review your AITWIRE recommendations and Brand Canon; file corrections for your approval.
Trading
4.1/10Trade 16 crypto exchanges + MetaTrader 5 from your AI assistant via one MCP connection.
Ask Ai
4.1/10Ask questions across Shopify, Klaviyo, GA4 and 20+ e-commerce sources in plain English.
Job Board Operator
4.1/10Connect Claude, Cursor, Codex, and other MCP clients to manage your Cavuno job board.
News
4.1/10Search structured COMPAMIR news in Japanese and English, with links to source reports.
Cbm
4.1/10Calculate shipment volume (CBM/CFT), weight, and how cargo fits standard shipping containers.
X402 Research
4.1/10Free agent discovery + paid x402 research (outline 0.01 / brief 0.02 USDC Base).
Event Synoptic
4.1/10Live LA events, ticket price comparison, bars & nightlife with real-time happy hours
Fed Spend
4.1/10Federal contract intelligence: $7T+ awards, SAM.gov opps, pWin verdicts, recompetes, protests.
Public Research
4.1/10Search public Hedge Fund Alpha metadata and find official membership and data product pages.
Decision Reflection
4.1/10Native Clarity decision mapping, MindScan episode reflection, and read-only evidence tools.
Payment Authority
4.1/10Analyzes delegated AI payment authority and exposes supported Stripe/x402 evidence contracts.
Weather
4.1/10Multi-model weather forecasts: point series, model scoreboard, and gridded fields. No auth.
Monitoring
4.1/10Client-website monitoring for agencies: uptime, incidents, SSL/domain expiry, server metrics.
Policylayer
4.1/10The system of record for AI agent authority: playbooks, routed policy questions, reusable rules.
Recognitium
4.1/10A memory your AI can prove and the market of the present tense. SHA-256, verifiable offline.
Signals
4.1/10Beta. Pay-per-call eCommerce competitive intel: pricing, promotions, history, AI-readiness.
Shortgenius
4.1/10Generate AI short-form videos and auto-publish them to TikTok, YouTube, Instagram, Facebook and X.
Sateais
4.1/10Satellite SAR analysis: ship, oil slick, building change, and time-series change detection
Sophon Consulting
4.1/10Read-only, deterministic AI triage and readiness tools implementing Sophon's published rubrics.
Bsv Cx
4.1/10Timestamp and verify evidence on-chain. Prove what your agent saw and when; verifying is free.
Constitution Lint
4.1/10Static linter for CLAUDE.md-style agent constitution files: 10 operational-guardrail checks.
Paperdock
4.1/10Create, edit and comment on LaTeX with AI agents in PaperDock, an independent Overleaf alternative.
Muze Cmo
4.1/10Run your ecommerce ads from Claude & ChatGPT: Meta, Google, Amazon, Shopify (150+ tools)
Fiscal
4.1/10Fiscal y nomina MX: recargos, ISR, CFDI, RESICO, calendario, IMSS, aguinaldo, finiquito.
Gphub
4.1/10Good Peeps retail-media data spine: clients, warehouse performance, meetings, agents. Team only.
Gateway
4.1/10Pay-per-call US government data: carrier safety, visa sponsors, contracts, employer risk.
MCP Server
4.1/10Vulnerability management: scan projects, search sealed packages, manage sealing rules and reports.
Innernet
4.1/10Your versioned memory across every AI tool — context maps, personal memory, and tasks over MCP.
Hunter Seeker
4.1/10Rank rows by outcome likelihood: deterministic pattern-detection and top-k prediction for agents
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.