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.
Zstudio
3.7/10ZStudio EIS MCP server: data validation, DRT, equivalent-circuit fitting, and plotting.
Occultron
3.7/10Crypto-paid uncensored LLM inference with signed execution receipts. No account.
Jartic Japan Traffic MCP
3.7/10JARTIC Japan traffic volume MCP | apify.com/fruitful_quintessence | atushi5.gumroad.com/l/kutuxe
Data Report MCP
3.7/10Local-first CSV/XLSX analysis report MCP server (stats, Excel charts, Markdown), no upload.
Web Extract MCP
3.7/10Local HTML to structured extraction MCP server (links, tables, title, body), offline.
Dsh Customs
3.7/10Read-only MCP server that checks a Chinese customs declaration ledger for internal inconsistency.
X Tkn MCP
3.7/10Lets an AI agent hand a secret to a person as a one-time link, with no way to read it back.
Adapstory Isa
3.7/10Local macOS arm64 vault with a stdio bridge. Install and open the bundled ISA app first.
Arketum
3.7/10Verified lifecycle for building software with an agent: units, human gates, requirements.
Feishu MCP Standalone
3.7/10Single-owner Feishu MCP: run your own service, configure your app, authorize your Feishu account.
Game Translator
3.7/10游戏文本本地化 MCP:多格式解析、批量翻译、回写
Mc Modpack
3.7/10整合包元数据管理与发布检查(mods、版本、加载器)
X402 Paid Checks
3.7/10Domain, email, vendor and ransomware checks paid per call in USDC via x402 from your wallet.
Consulta Boletines Oficiales
3.7/10Legislación consolidada, sentencias del TC, BORME, BOPV y normativa de la UE, con citas verificadas
MCP Server
3.7/10Your coding agent adds Probecast uptime monitors and reads incidents for projects you ship.
Capguru MCP
3.7/10AI captcha solver for agents: reCAPTCHA, hCaptcha, Turnstile, FunCaptcha, GeeTest, SmartCaptcha
Tsiky
3.7/10Turn your photo into a cartoon character and make animated explainer videos, step by step
Houyidb MCP
3.7/10MCP server exposing HouyiDB vector search, collection status, and opt-in writes.
Agentic Os
3.7/10Read-only, never-executing MCP server for the agentic-os governance, SDLC, and QE methodology.
Devlens MCP
3.7/10Production TypeScript & JavaScript AST code analysis and risk assessment MCP server.
Solwyn
3.7/10Check budgets before AI spend, record what your code spends and read Solwyn costs.
Stackvitals
3.7/10Known flaky tests, failing and slow CI, review flow, delivery and dependency risk from kept history.
MCP Server
3.7/10Fine-tune a small model on your data and benchmark it against your LLM API, in your AWS account.
Mytollbooth Calendar MCP
3.7/10x402 scheduling API: availability, conflicts, multi-party coordination for AI agents.
Squire
3.7/10MCP server for Appium mobile automation on iOS and Android devices with test creation tools.
Korean Parenting MCP
3.7/10한국 임신·출산·육아 정보 MCP 서버
Tracklint
3.7/10Decode GA4, Meta, TikTok, Microsoft UET requests and Google Ads conversions; check Tracklint plans.
Flint
3.7/10Agent long-term memory with search, recording, and hot injection for AI coding agents
Dirtsmith Evidence Quote Check
3.7/10Bind agent citations to admitted source text with spans and optional stale-hash rejection.
Freeflowchart
3.7/10Render text-based flowcharts (FlowScript) to PNG/PDF/Markdown with layout feedback, offline.
Image Toolkit MCP
3.7/10Local batch image MCP: resize, convert, compress, watermark, strip EXIF. Offline, no API key.
Zai Coding Plan MCP
3.7/10Z.ai GLM Coding Plan web search, page reading and GitHub repo docs as local MCP tools
Bulu Browser
3.7/10Drive a real Chrome via CDP + Playwright: snapshots, click/type, screenshots, network inspection.
Capimail
3.7/10Email for AI agents: send, receive and reply in threads, validate addresses, OTP, docs.
Reliable
3.7/10Resilient LLM/Agent calls via MCP: circuit breakers, timeout, jitter backoff, retry-storm guard.
Davincibets MCP
3.7/10AI sports predictions for NBA, NFL, NHL & MLB — picks, cards, track record, schedule
Md Semantic Search
3.7/10Local semantic search + citation-first RAG over Markdown. Hybrid dense+BM25F, ANN, MCP server.
Mersad
3.7/10Shared memory for AI agents: bi-temporal facts, first-class decisions, owner-resolved conflicts.
Latam Tax Id
3.7/10Validate Latin American tax IDs offline: MX RFC, CL RUT, PE RUC, CO NIT. No API key.
Selenium Webdriver MCP
3.7/10Selenium Tools for MCP
Cgajs MCP
3.7/10Compile CGA rules into 3D models (GLB) via the CGA.js cloud API; quota query included.
MCP Server
3.7/10Generate CGA rules from natural language via the NL2CGA cloud API (Chinese/English).
Swift Sure
3.7/10Swift code index for coding agents: type digests, symbol lookup, structural search.
Twitterdown
3.7/10Resolve public X posts into video links and manage your TwitterDown Agent API account.
MCP Papra
3.7/10Search, read and tag your Papra documents from Claude. Read-only by default, demo mode.
Nixie MCP
3.7/10Hand coding tasks to Nixie, a bring-your-own-key AI coding agent; get back its reply and changes.
Test MCP Server
3.5/10Alpic Test MCP Server - great server!
MCP Server
3.5/10Public MCP server for the LLM Search Engine
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.