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.
Public
4.7/10Reliability and bottleneck simulation for manufacturing lines; run experiments, sweep buffers.
Public
4.7/10Reliability statistics — Weibull/lognormal fitting, MTBF/MTTR, availability, system composition.
Public
4.7/10Run Plant Builder production-plant simulations with tunable knobs for goals, rates, and shifts.
Treasury
4.7/10Non-custodial USDC yield vaults on Base mainnet with 9 MCP tools for AI agent treasury.
Observatory
4.7/10Coordination Intelligence: AI infrastructure coordination dynamics across geopolitical blocs
MCP Server
4.7/10Norwegian company intelligence: ownership, roles, financials, risk, KYC/AML/PEP (multi-source)
Academy
4.7/10The Academy curriculum as an offline MCP library. Hosted course connector adds progress.
MCP Server
4.7/10API do Music360 para agentes de IA - artistas, obras, fonogramas, contratos, shows, tarefas e mais
Cityparity
4.7/10Cost-of-living & quality-of-life comparison: take-home pay, equivalent salary, safety-net deltas.
Marketing MCP
4.7/10Read-only ROSCA and savings-circle answers and calculators, from Wiremi's public facts.
Memxus
4.7/10Persistent memory layer that saves and recalls your project context and preferences.
Threadminder
4.7/10Persistent context for Claude. Your AI always knows your projects and next actions across sessions.
Superforms
4.7/10Human-input bridge for AI agents with voice-first answer links, MCP tools, and HTTP APIs.
Quote
4.7/10UK/EU and international car transport quotes with HMRC, IVA, DVLA and logistics costings.
Tastemaker
4.7/10Pull your TasteMaker brand kit + generated Agent Skill into your coding tool. Read-only.
MCP Server
4.7/10Artifact store for AI agents. Hosted OAuth at mcp.artifacta.io/mcp; local stdio via npm/PyPI.
Whataplan MCP
4.7/10Descubre eventos en España: filtra por texto, categoría, ubicación, precio y fecha. 38 categorías.
Openwarrant
4.7/10Document forensics: tamper/AI checks, extract, identity, PII, adverse media. No API key needed.
Platform
4.7/10Makes websites AI-agent-ready via MCP. Each property gets its own hosted MCP server.
Iwant
4.7/10Demand-side commerce: agents post a user's purchase intent, get ranked cross-source matches.
Agent Transaction Control
4.7/10Issue Agent Passports and verify agent authority before value moves. Signed verification records.
Validator
4.7/10On-demand drift checks: declared CSS color, radius, spacing & type vs your own tokens or a pack
Decisions
4.7/10Verified US tax and money decision tools: verdict plus a pre-filled deep link to the full page.
Decision Intelligence
4.7/10Log, evaluate, and ground AI decisions against authority context. Returns PASS, WARN, or BLOCK.
Graph Query
4.7/10Architecture-grounded query for AI agents. Governance constraints, system dependencies, evidence.
Transformation Radar
4.7/10Transformation readiness gaps and initiative risk signals for AI agents and enterprise change leads.
Tmtb Platform
4.7/10AI marketing skills for e-commerce brands: reports, campaign management, and creative generation.
Openwarrant Aitext
4.7/10Probability prose is AI-written, with the tells behind the score. No API key — text or URL in.
Openwarrant Verify
4.7/10Fact-check citations: resolve, match, support claims; math rechecked. No API key — URL in.
Moddable Games Tools
4.7/1015 tools for chess variant analysis, hex map generation, and board game utilities
Api
4.7/10AI document intelligence: extract, summarize, claim-check, notarize, and signed action receipts.
MCP Server
4.7/10Embodied AI & robotics MCP — 180+ companies, funding, Pulse, sector data (CC BY-NC 4.0)
MCP Server
4.7/10Let Claude, Cursor, or ChatGPT author Mermaid diagrams your team can read and share.
Haunt
4.7/10Public pages to clean JSON or Markdown, plus bounded site mapping and crawl. Failed calls are free.
MCP Server
4.7/10Create content and test it on a real audience — neuroflash Digital Twins inside Claude & Cursor.
MCP Server
4.7/10Blame things on blame.today, the anonymous 'who do you blame today' board. Nostr, no account.
MCP Server
4.7/10Lusha MCP server for authorized business profile, usage, and buying-signal insights.
Infranode
4.7/10Keyless open data for 84 German cities: 12 lean read-only MCP tools covering 67 data types.
Event Registration
4.7/10Event registration at scale: events with photos, waitlists, virtual queues, and dynamic pricing.
Tinyfn
4.7/10500+ deterministic tools for AI agents: math, conversion, validation, hashing, encoding, date/time.
MCP Server
4.7/10Live NFL, MLB, and NBA sports intelligence: injury signals, identity resolution, projections.
Allowance MCP
4.7/10Secure agent purchasing with human-approved virtual cards, receipts, and audit trails.
MCP Server
4.7/10Information, FAQs, features, and pricing for Fluentive's task management platform.
Atlas Mind
4.7/10Self-hosted git-native knowledge base with an MCP endpoint your AI reads, writes and rewinds
Aitv
4.7/10Remote MCP server for AI.TV creators — delegate account operations to your AI agent over MCP.
Insights
4.7/10Query your customer feedback: studies, themes, suggestions, tags, and sentiment trends.
Salta
4.7/10Mobile-first AI life planner — turn goals into daily, synced tasks from your AI assistant.
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.