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.
Skillworks
4.3/10SkillWorks: Search published Claude Code skills, plugins and marketplaces.
Stacktab
4.3/10StackTab: SaaS service pricing and monthly stack cost estimates.
Stillshipping
4.3/10StillShipping: Check whether a developer tool is still maintained.
Storeready
4.3/10StoreReady: Whether AI app builders produce apps that pass App Store review.
Tooldrift
4.3/10ToolDrift: Current AI model pricing and which models coding tools route to.
Miru
4.3/10Hybrid semantic and keyword code search for coding agents.
MCP Server
4.3/10Check whether a URL or IP is safe before an AI agent fetches or opens it.
Control
4.3/10Control ESP32 IoT devices from AI agents: status, GPIO, ADC, reboot.
Mxik
4.3/10Search MXIK (IKPU) product codes of Uzbekistan on tasnif.soliq.uz. Unofficial.
Rustjunosmcp
4.3/10Juniper Junos/SRX MCP server: scoped, audited, two-person change control. Rust.
Pg Bloat Detective
4.3/10Read-only Postgres bloat verdicts: blockers, timelines, REINDEX proof.
Unitares
4.3/10Accountability infrastructure for long-running AI agents.
Custovox Sentiment
4.3/10Custovox AI customer sentiment analysis MCP server
MCP Api Guardian
4.3/10Local OpenAPI contract and breaking-change checks for AI agents.
MCP Cost Optimizer
4.3/10Local-first LLM cost analysis and model-switch savings estimates for AI agents.
MCP Database Doctor
4.3/10Offline PostgreSQL query, migration and EXPLAIN diagnostics for AI agents.
MCP Dependency Doctor
4.3/10Read-only npm dependency diagnostics for AI coding agents.
MCP Seo Auditor
4.3/10Read-only static SEO audits and bounded crawling for AI agents.
Zennodroid
4.3/10Create, configure, start and monitor ZennoDroid tasks and their sessions.
Zennoposter
4.3/10Create, configure, start and monitor ZennoPoster tasks and their sessions.
Prinfer
4.3/10TypeScript inferred types, completions and type errors for AI coding agents
Macos MCP Server
4.3/10Local macOS 27 desktop automation through MCP on Apple silicon.
Ffc
4.3/10Read and change documents, reports and workflows on Frappe and ERPNext sites.
Typeprobe
4.3/10TypeScript inferred types, completions and type errors for AI coding agents
Portage
4.3/10Serve a Shopify store's catalog to AI shopping agents over MCP (read-only).
Sstim
4.3/10SSTIM reference for senses, stimuli, perception and scientific contributions.
Searchio
4.3/10Keyless web search and page reading for AI agents, built to get past bot walls.
Architecture Intelligence Platform
4.3/10Evidence-qualified architecture context for coding agents.
Llm
4.3/10Let a planning agent hand bounded language work to a local Ollama model.
Ascapi
4.3/10Forget Fastlane, this is the app stores coolest API.
Proxbase
4.3/10Create, test and break real Proxmox VE clusters in QEMU/KVM on the local host.
Webcam
4.3/10Give LLM agents webcam access: capture photos and record short videos over MCP.
Staan MCP
4.3/10Web search with full-page content and grounded answers from the Staan API.
Reverseport
4.3/10Reverse engineer anything. Port it anywhere. One MCP server for coding agents.
Nexus MCP
4.3/10Search Notion and Supabase through one safety-focused MCP server.
Rustmistmcp
4.3/10HPE Juniper Mist MCP server: scoped, audited, two-person change control. Rust.
MCP Server
4.3/10Identify what an AI image carries (marks, metadata, watermarks), then clean it.
Addy MCP
4.3/10Manage addy.io email aliases, recipients, domains, rules and blocklist.
Codeagent Memory
4.3/10Local code graph and solution memory for coding agents via CLI and MCP.
Motozmo
4.3/10Search motozmo.com's motorcycle repair guides and gear reviews.
Maxgraph
4.3/10Self-hosted persistent memory for AI agents: knowledge graph and hybrid search.
Lawn Mowing Calculator MCP
4.3/10Lawn area, mowing time and mowing price estimate tools for AI assistants.
MCP Server
4.3/10Search, rank and compare open-source AI projects with Archestack's open data
Youtube Channel
4.3/10YouTube channel profiles and recent video inventories. Paid FlashData API.
Mama Rich MCP
4.3/10公式ママ活ママリッチの公開記事を検索し、タイトル・説明・出典URLを返すMCPサーバー
Wpmission MCP Server
4.3/10WPMission MCP server for WordPress management product information.
Network Tools
4.3/10Free network diagnostic tools: IP info, DNS lookup, IPv6 check. No API key.
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.