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.
MCP Server
4.1/10跨客户端 ECharts 图表 MCP server:数据 -> 可交互 HTML 与内联图片
Korail MCP
4.1/10한국철도공사(KORAIL) 공공데이터 MCP 서버 — 98개 도구, API 키 신청 불필요. 역·열차·화물·통계 데이터 자연어 조회.
Nockchain MCP
4.1/10Moved to io.github.winter0x/nockchain-mcp. This entry is no longer updated.
Prefab
4.1/10List, create and deploy your Prefab project templates from any MCP agent.
MCP Server
4.1/10OpenStreetMap queries as MCP tools, served by the Overspan hosted Overpass API.
Wisegrid MCP
4.1/10Read and write WiseGrid sheets, rows, columns and reports from any AI agent.
Profitplay MCP
4.1/10MCP server for the live ProfitPlay BTC five-minute AI agent sandbox
Ecoscope
4.1/10Agent-native ecological data discovery, analysis, visualization, and provenance
Unifi MCP
4.1/10MCP server for Ubiquiti UniFi Network and Protect. 63 tools, 16 agent skills.
Recolx MCP
4.1/10Read-only access to your Recolx recordings, transcripts and templates (stdio)
MCP Server
4.1/10天启至数 ApocData - MCP Server for A-share market data (46 free, no-auth endpoints)
Gstinapi MCP
4.1/10GSTIN verification, GST filing history and HSN/SAC lookup for India.
MCP Light Memory
4.1/10Local-first persistent memory for coding agents and MCP clients.
MCP Einvoicing Ae
4.1/10MCP server for United Arab Emirates electronic invoicing
Evoburrow MCP
4.1/10Unofficial guarded A1 Evo AcoustiX, REW, and Denon/Marantz calibration tools.
Stallhunt
4.1/10Evidence-backed Linux performance triage over MCP
Evidence Gate
4.1/10Local checks for artifacts, declared claim evidence, and citation containment.
Release Gate
4.1/10Local completion-contract checks and release receipts.
Remind MCP
4.1/10Read Remind classes, chats and messages, and manage notification settings.
MCP Invoicenow Sg
4.1/10MCP server for Singapore electronic invoicing (InvoiceNow)
Mcpify
4.1/10Focused, production-ready CLI: turn any OpenAPI REST API into an MCP server.
Mixx Dj MCP
4.1/10FastMCP server for Mixxx DJ software control via OSC protocol
Yahboom MCP
4.1/10SOTA 2026 Yahboom Raspbot v2 ROS 2 MCP Server
Doc Extract Api
4.1/10SchemaLock — paid extraction: JSON from docs via your schema, x402/USDC.
Global Intel Exchange
4.1/10Real-time sanctions screening, CVE, and company registry checks for agents.
Elite Reasoning MCP
4.1/10Evidence-gated verification, selection, and measurement MCP for coding agents.
Koda
4.1/10Verification and memory layer for coding-agent workflows.
Aeron Wallet
4.1/10Non-custodial agent wallet for Robinhood Chain. Pays x402 requests in USDG.
Getbirthchart MCP
4.1/10Official MCP server for GetBirthChart astrology calculations.
Yad Agent MCP
4.1/10MCP wrapper for Yad, a local browser-automation companion, for coding agents.
X402 Express
4.1/10Express.js HTTP 402 payment middleware for AI agent micropayments
Wilddatum
4.1/10Agent-native ecological data discovery, analysis, visualization, and provenance
Repo Release Tools
4.1/10Config-driven branch and release helpers for Git repositories
Release To Tasks
4.1/10Convert public release-note URLs into ordered, source-cited upgrade tasks.
Lunchmoney App
4.1/10MCP-first access to your Lunch Money data.
MCP Ooxml Ledger
4.1/10Edit Office documents and prove no edit went unrecorded
Marzban MCP
4.1/10Manage Marzban panels through the Model Context Protocol.
Solana Snipe Bot MCP
4.1/10Autonomous Solana meme-coin sniper bot with 40 MCP tools for AI control.
Api Test MCP
4.1/10Call the real API and check the response against your OpenAPI spec.
Montycat MCP
4.1/10Shared, persistent memory for AI agents, with semantic recall and live updates.
Firefox Css Theme
4.1/10MCP for building, inspecting, and live-debugging Firefox CSS themes.
MCP Ollama Vllm
4.1/10Call your local Ollama or vLLM model over MCP with schema-validated JSON output
Flywizz MCP
4.1/10Search Wizz Air flights from your AI agent. Unofficial.
Sparda MCP
4.1/10AI writes. SPARDA proves. Deterministic, offline security gate for AI edits.
Policyvault
4.1/10Non-custodial Kaspa policy enforcement for AI agents; signers retain custody.
Rebuild Dossier
4.1/10MCP server that reverse-engineers a locked rebuild spec from an existing app.
Kilawatt MCP Server
4.1/10Kilawatt Cloud MCP server: request GPU compute with account or x402 payments.
Wrapguard MCP
4.1/10Detect unnatural Korean and English mid-word wrapping in responsive web pages.
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.