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.
Netbox MCP
4.3/10MCP server for NetBox DCIM/IPAM with read-only and dry-run modes
Oxidized MCP
4.3/10MCP server for Oxidized network device configuration backups
Grill
4.3/10A second opinion from an unrelated AI model before you commit to a decision.
Say Ur Intent
4.3/10Local-first Sui DeFi evidence and review for AI clients before wallet signing.
Lockkeeper
4.3/10Routes each task to the few skills, MCP servers and tools that fit it.
Forgejo MCP Rs
4.3/10Model Context Protocol server for Forgejo, Codeberg and Gitea, in Rust
MCP Server
4.3/10Ask a human before your agent acts: approval requests decided on a phone.
Opensolar MCP
4.3/10Unofficial, self-hosted MCP server for the documented OpenSolar API.
Memoryguard
4.3/10Local-first governed MCP memory backend for coding agents.
Laogu MCP
4.3/10老谷拆财报 MCP Server:21 个 A 股财经 skill 的程序化数据层(零 key、纯公开接口)。
Expense Report
4.3/10Expense report builder: log expenses, categorise, split VAT, export from chat.
Trekking MCP
4.3/10Italian trails, huts, avalanche bulletins and elevation weather
Doubleoh MCP
4.3/10The fix desk for AI agents: human fixes become skills the whole fleet reuses.
Linkbit MCP
4.3/10Shorten URLs, bulk create, QR, and click analytics for LinkBit.
Crw
4.3/10Open-source web scraper for AI agents with scrape, crawl, and map tools
Aicb Roslyn MCP
4.3/10Symbol-aware C# and .NET code context for AI coding assistants.
Keyline
4.3/10Design engine for AI agents: images at every size, no Chrome, 2× fewer tokens
MCP Server
4.3/10Send native LinkedIn voice notes from your AI assistant via the Svara API.
Jevmem
4.3/10Automatic project memory for Claude Code. Also works with Cursor and Codex.
Claimgate
4.3/10Flag marketing claims your evidence cannot substantiate, before you publish.
Browser Buddy
4.3/10Let AI coding agents read pages through your real, logged-in Chrome browser.
Blender MCP
4.3/10Drive a local Blender headlessly: inspect, convert, render and script 3D files.
Verificar Curp
4.3/10Valida, coteja y verifica CURPs mexicanas en el registro de RENAPO.
Prompteden MCP
4.3/10Stdio MCP server for PromptEden projects, monitors, answers, and analytics.
Datum MCP Server
4.3/10Agent-native marketplace: buy and sell datasets, snapshots and solved problems.
Storeshots
4.3/10Turn raw app screenshots into App Store and Google Play marketing screenshots.
Nolicense Nearby MCP
4.3/10Search 880+ artist-owned tracks and get sync licenses for social, TV and film.
Tree Sitter MCP Server
4.3/10Parse code into Tree-sitter ASTs to see node kinds, field names, and positions
MCP Confirm
4.3/10An MCP server whose confirmation cannot be replayed against a different call.
Linkbit MCP
4.3/10Shorten URLs, bulk create, QR, and click analytics for LinkBit.
Desktop
4.3/10Local MCP access to Stochastly desktop nodes, diagnostics and research tools.
Dbcode
4.3/10Query and explore 100+ databases through your DBCode connections.
Veto
4.3/10Turn OpenAPI services into tools an agent can call under your rules.
Designfit
4.3/10Validate AI-built front-ends against Figma by tokens and geometry, not pixels.
Sui MCP
4.3/10Local-first Sui DeFi evidence and review for AI clients before wallet signing.
Galactic Bridge MCP
4.3/10Find LayerZero OFT bridge routes by contract address across 14 EVM networks.
Pantry Relay
4.3/10Local SQLite pantry planner with six MCP tools for meals, stock and shopping.
Postlane
4.3/10Send transactional email and read send activity through the Postlane API.
Content Router
4.3/10给素材做 11 维内容画像,推荐跨媒介输出形态(PPT/信息图/短视频/漫画等 6 种)并给出可执行调度提示词
Memory Dream Engine
4.3/10零 LLM 事实提取 + 三维信号评分 + 艾宾浩斯衰减 + 五阶段梦境流水线与内容发芽检测,纯计算零依赖
Pattern Radar
4.3/10把 AI 答案/竞品内容当语料,找出反复出现的说法、被反复引用的信源与答案同质化程度,含对照组自检
Talos MCP
4.3/10Talos MCP is an opinionated MCP server for Talos Linux
Zerostel
4.3/10Checkpoints, timeline and rewind for AI coding agents. Local, no telemetry.
Littlejohn MCP
4.3/10Local Robinhood Chain MCP and transaction review runtime.
Blockdex
4.3/10BlockDex: Search shadcn-compatible components across public registries.
Kitgrade
4.3/10KitGrade: Starter kits and boilerplates, graded by installing them.
Rulestack
4.3/10RuleStack: Search real AGENTS.md, CLAUDE.md and Cursor rules files.
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.