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.
Relay
3.7/10把要办的事转给已接入的产品去办:搜索动作、发起调用、用户确认、查询结果。
Agent Services
3.7/10Paid deterministic CSV cleanup and source-HTML checks. x402 USDC on Base.
Smart Calendars Ai
3.7/10Create and update subscription calendars from ChatGPT, Claude, or Codex.
MCP Server
3.7/10Deploy web game builds and read playtests: who played, errors, feedback, bugs.
Madda Tasks
3.7/10Project scheduling: Gantt chart, dependencies, baselines, reports and AI agents
Sunsetdiff
3.7/10AI model shutdown dates, replacements, and migration diffs. Free, no API key.
Conformance Oracle
3.7/10Pair-level MCP+A2A conformance verdicts for the exact pair you delegate across.
Vidkraken Docs
3.7/10Search and read the Vid Kraken API docs, guides and pricing. No sign-in needed.
Spritefetch
3.7/10Search and download free CC0 2D sprite sheets and tilesets for games.
Vamos
3.7/10Organize group trips, track shared expenses, and see who owes whom in Vamos.
Sitecheck Jobs Property
3.7/10112 pay-per-call agent tools: job market and real estate data tools. x402
Solana Wallet Intel
3.7/10Solana wallet risk and intel, x402 USDC pay-per-call (Cloudflare host).
Memento Team
3.7/10Parallel coding agents claim a file before editing, so none overwrites another.
Tienda
3.7/10Tiendas de uniformes escolares: buscar prendas, talles y armar el carrito.
MCP Server
3.7/10AaaSagent: browse agent templates (BYOK) and join the invite-only beta.
Apiant
3.7/10Build, run and manage APIANT automations across hundreds of apps.
Getfit
3.7/10Build a workout that fits your time, gear and body — free, no sign-in.
MCP Server
3.7/10Manage CloudBT VPS and virtual data center servers in Istanbul with AI agents.
Rowbrief
3.7/10One project plan that you, your team and each of your AIs read and write.
MCP Server
3.7/10Evidence-backed project memory and checkpoints for AI coding agents.
Approval Durability Census
3.7/10Cross-domain census of approved-but-not-completed work, by cause and type.
Agent Identity
3.7/10Give your AI agent its own email inbox, phone number and agent-to-agent tasks.
Wead
3.7/10Read-only info on WeAD apps, status, abstracts and public documents.
Fet112
3.7/10Security intelligence for AI agents monitoring Ethereum before actions.
Travel Esim
3.7/10Travel eSIM plans from haalaan; returns only destinations currently available.
Lobstermatch
3.7/10Tools for finding agents, dialogs, and completed work on LobsterMatch.
Sds Extraction
3.7/10Extract safety data sheet (SDS/MSDS) PDFs into a fixed 16-section JSON record.
Bilkalkylen
3.7/10Swedish car advice: monthly cost, find and compare cars, leasing campaigns.
Roadmap
3.7/10Reads a Pilotless roadmap after OAuth sign-in. Scope is roadmap:read only.
Devstackpulse
3.7/10Breaking changes and weekly digests for the APIs and SDKs in your dev stack.
Hotrepo
3.7/10GitHub Trending boards and AI-written reviews of trending open-source projects.
Perfect Clock
3.7/10Find meeting times across time zones and compare working hours.
Beaches
3.7/10Live swimming and family conditions and reviewed guides for 77 Mallorca beaches
Agenthands
3.7/10Human-reviewed real-world actions for AI agents.
Labs
3.7/10Search accredited testing labs and verify lab scope evidence from ScopeMatch.
Docs
3.7/10Read-only Hebrew travel insurance guides and FAQ published on checko.co.il.
Alphamotion
3.7/10Digital, ecommerce, operations, compliance and finance for brands in India.
Il Co
3.7/10Source-backed handoffs from Slack, Linear and GitHub, approved by their author.
Housewarming Gifts
3.7/10Hand-picked gift ideas for housewarmings, turned into shareable wishlists fast.
Loops
3.7/10Draw causal loop diagrams in the chat and edit them on a shared link.
Bugtape Demo
3.7/10Read-only sample shop with captured bug evidence. No account or key needed.
Chipp Memory
3.7/10Chipp: a project's memory, circles, and scheduled tasks
Chipp Newsletters
3.7/10Chipp: newsletter topics, audiences, contacts, campaigns and sends
Account
3.7/10Work in your workonit account: people, records, app actions and AI agents.
Diagrams
3.7/10Create and revise scientific and educational diagrams with ConceptViz.
Anymark
3.7/10Create logos from templates made by humans (no AI slop)
MCP Server
3.7/10Query and act on your Ostorlab scans, vulnerabilities, tickets and assets.
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.