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.
Bluffnet
4.1/10Live Texas Hold'em for AI agents. The tools teach the rules; the bluffing is up to your model.
Fable 5 Agent
4.1/10Authenticated async Fable 5 Agent agent with status polling and artifact results.
Gpt 5 6 Luna Agent
4.1/10Authenticated async GPT-5.6-luna Agent agent with status polling and artifact results.
Gpt 5 6 Sol Agent
4.1/10Authenticated async GPT-5.6-sol Agent agent with status polling and artifact results.
Opus 4 8 Agent
4.1/10Authenticated async Opus 4.8 Agent agent with status polling and artifact results.
Sonnet 5 Agent
4.1/10Authenticated async Sonnet 5 Agent agent with status polling and artifact results.
Mdapi
4.1/10Web page or HTML to clean LLM-ready Markdown or JSON. x402 pay-per-call, $0.005, no API key.
Euearth
4.1/10An agent-first commons: merit crowns each domain's open model; standing is earned, never bought.
Quotefirst
4.1/10Get dollar quotes from 200+ LLMs before any work runs; accept, execute, and verify quality.
Scrap Autos MCP
4.1/10Instant Canadian scrap-car value quotes by year/make/model, provincial rates, and pickup leads.
Pricing
4.1/10Compare up-to-date pricing for 40+ LLMs (incl. Chinese) & estimate cost from tokens. EN/zh.
Registry
4.1/10What a domain publishes for AI agents: ai-catalog.json, llms.txt, agents.md, robots.txt rules. Free.
Cms
4.1/10UXBERT Labs headless CMS: model, write and publish bilingual content, media, delivery checks.
Weather
4.1/10Multi-model weather forecasts: point series, model scoreboard, and gridded fields. No auth.
Call Me
4.1/10Calls your phone when an AI task finishes or is blocked — hear it, say what's next.
The Aggregate
4.1/10LLM rankings from public benchmarks, model comparisons and source-linked results. Updated daily.
Genomic Intelligence
4.1/10Hosted DNA language models: promoter, splice, enhancer, chromatin, expression, annotation
Fotohub
4.1/10Generate images, video, music, voice and 3D through one API. 30 tools, 200+ models.
Hokai
4.1/10Query the HokAI catalogue of AI tools, agents, models, companies and infrastructure services.
Pantts
4.1/10Read and manage your Pantts boards — kanban, gantt, table and graph over one shared card model.
Isitdeprecated
4.1/10Check if an AI model is deprecated, retiring, or silently changed price or context window.
MCP Server
4.1/10Image, video, music and text generation across 100+ models through one endpoint.
Studio
4.1/10Run 70+ AI models and 50+ tools on CNAPS Studio in natural language — Claude, n8n, or Zapier.
Mascotlab
4.1/10Generate your app's mascot, then props, poses and animations that stay on-model.
Noveum
4.1/10Trace, evaluate, and optimize your LLM, RAG, and agent apps with Noveum observability.
Retail Media Measurement
4.1/10Retail media measurement in Gus Dantas's own words. No model inside: every answer is text he wrote.
MCP Server
4.1/10Build a real 3D website by chatting: pages, models and text in space, published to a live URL.
Credcycle
4.1/10Provider credentialing & payer-enrollment tracking for medical practices — read-only demo tools.
Video Transcript
4.1/10Any video URL to LLM-ready transcript. ASR built in, no captions needed. TikTok, X, TED and more.
Models
4.1/1061 verified financial models and a household planning engine: 20 MCP tools, 6 keyless, specs cited.
Whatif
4.1/10Conversational what-if simulation: build, diagnose and compare Petri-net models; CC0 catalog.
Agent Continuity
4.1/10Resume the work, not the conversation. A checkpoint by one model is resumable by another.
Frontier
4.1/10Discover Frontier inference capabilities and read sanitized usage through read-only tools.
Fullmakt
4.1/10Credential broker for AI agents: scoped, revocable API access with policy enforcement and audit.
Orq
4.1/10Build and monitor LLM apps on Orq.ai: AI gateway, agents, prompts, evals, traces.
Token Counter
4.1/10Counts tokens under OpenAI-compatible (tiktoken) encodings, by model or encoding name.
Gpt 4O Ksdwzw
4.1/10GPT-4o: GPT-4o (“o” for “omni”) is our versatile, high-intelligence flagship model. It accepts both.
Gpt 5
4.1/10GPT-5: GPT‑5 is OpenAI’s most advanced and unified AI model, combining fast, real-time.
Openai Sora
4.1/10OpenAI Sora: Sora & Sora 2 (new social media like TikTok) API by ChatGPT creator OpenAI. Access.
Swift Ai
4.1/10Swift AI: Access a wide range of AI models⚡, including OpenAI 🤖,DeepSeek 🔍, Claude 🧠, Gemini 🌟, and.
Anansi Data
4.1/10Time-series nobody else archives: LLM price history, prediction markets, gas, perp funding.
MCP Server
4.1/10Generate game-ready 3D models, textures, and audio from natural language, over MCP.
MCP Server
4.1/10Confidential compute and inference sold to agents over x402 USDC, plus an agent wallet over MCP.
Yappy Docs
4.1/10Yappy macOS docs (yappy.biz): setup, permissions, LLM backends, troubleshooting.
Memroam
4.1/10Portable AI memory that roams with you across models and harnesses - plain markdown you own.
Llms Txt
4.1/10Create, validate and audit llms.txt, incl. the Lighthouse Agentic Browsing check.
Memory
4.1/10Persistent memory for AI agents. Free, no LLM, no SDK. Open Worker you can self-host in 2 commands.
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.