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.
Ride Booking
3.9/10Book rides, get fare estimates, and manage trips across African cities with Rovv.
MCP Server
3.9/10Enables AI assistants to natively interact with the Serpzilla link-building marketplace.
Newtqnia
3.9/10Read-only access to NewTqnia news, terminology, and explainers in English and Arabic.
MCP Toolbelt
3.9/1029 pay-per-call DNS, SEO, SSL, security, and dev tools for AI agents. x402, no API key.
Roadflow
3.9/10Create and edit roadmaps with JSON or markup; share edit and view links from AI agents.
Overassessed
3.9/10Maryland property-assessment fairness checks vs similar homes, with appeal windows and links.
MCP Server
3.9/10CircleCI's MCP server: inspect projects, runs, workflows, jobs, logs, tests, and artifacts.
Public Knowledge
3.9/10Public EPK real estate listings and multilingual guides for Panama and the Dominican Republic.
Rtcstats
3.9/10Query analyzed WebRTC sessions: observations, deductions, experience scores, and AI summaries.
Consistency Gate
3.9/10Check claims against a fact-store: consistent, contradicts, or unverifiable — with a receipt.
Council Consult
3.9/10Stress-test a decision through named thinkers' lenses: assumptions, counter-arguments, receipt.
Values Firewall
3.9/10EU AI Act Art-14 runtime oversight: allow / flag / gate-to-human on an agent action, with receipt.
Escaparate
3.9/10Conectá tu cuenta de Escaparate y manejá catálogo, ventas, novedades e imágenes conversando.
Skills
3.9/10Find, call and pay per call: the capability layer for agents, plus skills. One key or OAuth.
Settlement Index
3.9/10See what actually settles on x402: wash-adjusted volume, payTo checks. Free, no key, no signup.
MCP Gateway
3.9/10Security & DLP proxy for MCP: tool-poisoning scans, PII redaction on tool args/results. Beta.
Property Intelligence
3.9/10French address intelligence: 18.6M sold prices, energy, risk, crime and schools — each sourced.
Phone Agent
3.9/10Outbound phone calls placed by an AI voice agent to book, ask, or confirm on your behalf.
Companies
3.9/10Verify a US company: officers, agents, motor carriers. Flags when our status disagrees with state.
MCP Server
3.9/10Connect AI assistants to PayRent to manage landlord portfolios, confirming changes first.
Promotion Allocation
3.9/10Ecommerce capital allocation: marketing budgets, advertising, merchandising, product portfolios.
Public Selling Agent
3.9/10Read-only product discovery, merchant trust, shipping and returns for SVV-Schatzoekers.
Meuportal Reservas Demo
3.9/10Portal de reservas: consulta datas, solicita reserva e retorna link de pagamento.
Freight MCP
3.9/10Real-time ocean freight rates, LCL pricing, and booking management for global logistics.
Translation
3.9/10Translate text or HTML, detect languages, and list supported languages with Langbly.
Markupbase
3.9/10Versioned artifact review for people and AI agents, with contextual comments and human control.
Marketplace
3.9/10AI marketplace for agents to find paid work and trade digital services via MCP and x402.
Tools
3.9/1049 deterministic tools for text integrity, agent control, and contextual quality evidence.
China Macro
3.9/10Pay-per-call China macro and supply monitors: revisions, FDI, LEI changes, 1688 suppliers.
Trade Logistics
3.9/10Pay-per-call shipping evidence: canal queues, tanker flows, container and carbon exceptions.
Talebuddy
3.9/10Turn a brainstorming conversation into a story bible of characters, locations, items, and lore.
Donebear
3.9/10Local-first task manager: create, edit, and complete tasks, projects, and checklists via MCP.
Commerce Demo
3.9/10Kaiva Bridge live demo: a commerce dataset as a hosted, read-only MCP server (6 tools).
Dependency Trust
3.9/10Trust-check any dependency for agents: OpenSSF Scorecard, licenses, CVEs, deps. 7 ecosystems.
Korea Stay
3.9/10Korean lodging: 84,490 stays from 4 government permit ledgers + KTO TourAPI, honest gaps
Chargt MCP
3.9/10Find EV charging stations, live availability and prices across the Netherlands via NDW data.
Loopertask
3.9/10AI-native Kanban board — connect Claude to claim, work and move your tasks over MCP.
Agent Newsstand
3.9/10Market data and web intelligence for AI agents, paid per call in USDC on Base via x402.
Utility
3.9/10Machine-native utility network: verified evidence services for autonomous agents.
Infrapulse
3.9/10AI agent infrastructure for discovery, authorization, execution, identity, and signed receipts.
Transaction Preflight
3.9/10Synthetic-only transaction screening with evidence and ES256-signed decision receipts.
Kangram
3.9/10Task & board management for AI agents + humans. Kanban, comments, digests via MCP.
Agentavow Trust
3.9/10Signed, offline-verifiable safety scores for the MCP servers, packages & tools an agent connects to
Public Site
3.9/10Read-only public information about InfoAddict, Dan Crane, services, and contact options.
Crm
3.9/10Open-source CRM your AI agents can write to: companies, people, deals, tasks, notes, pipeline.
Mayneart MCP
3.9/10Live Mayneart MCP server exposing the dynamic SELLABLE catalog with x402 execution.
Vide Vita
3.9/10Vidé Vita supplements — live prices, stock, label amounts, warnings, reviews and checkout
Instagram Insights
3.9/10Instagram MCP for public posts, comments, replies, users, and video/Reels speech-to-text.
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.