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.
Web
4.1/10Read any public page as markdown, link previews, URL safety, page audits, domain availability and…
Tao Reach Home
4.1/10T.A.O. — Reach home. Signed agent check-ins and a public roster; no agent execution.
Waypoint
4.1/10Useful public tools, sourced notes and opt-in research into discovery and agent cooperation.
Rank1
4.1/10Find relevant customer conversations, review reply drafts, and plan content with Rank1.
Aidata
4.1/10Google Analytics, Search Console, Ads, CRM, Cloudflare and more for your sites, from your own AI.
Site Search
4.1/10Read-only search over the aidata.stream documentation, blog, changelog, pricing and FAQ.
Crimp
4.1/10Plan DC electrical systems: find components, calculate circuits, check designs and create drafts.
Varexis Index
4.1/10Read-only evidence discovery and advisory previews for VAREXIS-INDEX; no advice or authority.
Suggestionbox
4.1/10Leave a private suggestion, problem or compliment for any business. Only the business reads it.
Clarity Today
4.1/10Clarity Today's briefing, latest stories by desk, search and full source-linked stories.
Website Feedback Tool
4.1/10Read visual design reviews from live web pages: comments, CSS selectors, styles, console errors.
Dr Novo
4.1/10Dealer gamma maps for SPY, QQQ, IWM and 90+ cryptos, plus NoVo's own session record. 20 free tools.
Fourth Take Studio
4.1/10Explore Fourth Take feeds and Subjects, work on private Thread drafts, and use Studio.
Investors
4.1/10Person-checked US VC firms and startup investors with verified work emails and LinkedIn profiles.
Asof
4.1/10Historical crypto wallet holdings, valuations and CSV exports. OAuth; paid own-wallet scans.
Asof Demo
4.1/10No-sign-up demo: recorded historical crypto wallet holdings, prices and CSV exports. Fixed examples.
Offers
4.1/10Make price offers on Shopify products; get counters, single-use codes and checkout links.
Connect
4.1/10Track public wallets: token balances, prices, portfolio value, DeFi positions and holding history.
Contextlayer MCP
4.1/10Personal context management for AI assistants
Ctxl
4.1/10Personal context management for AI assistants
Ctxl MCP
4.1/10Personal context management for AI assistants
Mcpcap
4.1/10An MCP server for analyzing PCAP files.
Server
4.1/10Family calendar, tasks, meals, lists & rewards hub for AI assistants.
MCP Server
4.1/10Send fiat payments via MCP with two-step confirmation and Stripe Connect.
Hypertool MCP
4.1/10Dynamically expose tools from proxied servers based on an Agent Persona
Deepcontext
4.1/10Advanced codebase indexing and semantic search MCP server
Codescene MCP Server
4.1/10An MCP server that provides CodeScene Code Health analysis tools.
Python MCP
4.1/10Local-only Python MCP server for the Files.com API.
Graqle
4.1/10Dev intelligence layer: 7 MCP tools for graph-powered codebase reasoning.
Druid MCP Server
4.1/10AI-powered MCP server for Apache Druid cluster management and analytic
Memory MCP
4.1/10MCP server for AI memory management using Letta - Standard MCP format
Nuget
4.1/10A Model Context Protocol (MCP) server for NuGet.
Quanttogo MCP
4.1/10Macro-factor quantitative signal source for US and China stock markets via MCP.
Verify MCP
4.1/10Offline Ed25519 verification of signed receipts, bundles, and trust artifacts.
Scout MCP Local
4.1/10An MCP server for Scout Monitoring data interactions.
MCP Server
4.1/10Open protocol for booking and scheduling professional services via AI agents
Constellation
4.1/10Code Intelligence Platform for AI Coding Agents
Grantai
4.1/10Persistent memory for AI agents. Infinite context with sub-millisecond recall.
Server
4.1/10Eyes and hands for AI agents on Android and iOS devices.
402 MCP
4.1/10AI agents discover, pay for, and consume any Lightning-gated API autonomously
MCP Server
4.1/10AI-powered household inventory — query everything you own via natural language
MCP Api
4.1/10Preview release of FusionAuth API MCP server
Unleash MCP
4.1/10MCP server for managing Unleash feature flags
Suwappu
4.1/10Cross-chain DEX for AI agents. Swap tokens across 7+ chains.
Skillhub MCP
4.1/10MCP server that exposes Claude-style skills to any MCP client.
Ai Scanner
4.1/10Scan codebases for LLM/AI SDK usage, exposed API tokens, and hardcoded secrets.
Ybe Check
4.1/10Ybe Check – security and compliance orchestrator for AI-generated repositories.
Neurohive
4.1/10Multi-agent memory intelligence with expertise tracking and conflict detection
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.