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.
Llm Orchestration Agent Langgraph
3.7/10LLM Orchestration Agent (Langgraph)
Llm Orchestration Agent Langsmith
3.7/10LLM Orchestration Agent (Langsmith)
Llm Orchestration Agent Openai
3.7/10LLM Orchestration Agent (Openai)
Llm Orchestration Agent Opentelemetry Api
3.7/10LLM Orchestration Agent (Opentelemetry Api)
Llm Orchestration Agent Opentelemetry Instrumentation Fastapi
3.7/10LLM Orchestration Agent (Opentelemetry Instrumentation Fastapi)
Llm Orchestration Observability Agent
3.7/10LLM Orchestration Observability Agent
Llm Orchestration Traced Agent
3.7/10LLM Orchestration Traced Agent
Structured Output Agent Openai
3.7/10Structured Output Agent (Openai)
Wattscope
3.7/10Tracks the estimated carbon footprint of AI model usage, per org and project.
Autotrade
3.7/10Deploy autonomous LLM trading agents and drive them over MCP.
Fable 5 1
3.7/10Authenticated async Fable 5.1 agent with status polling and artifact results.
Gpt 6 Astra
3.7/10Authenticated async GPT-6 Astra agent with status polling and artifact results.
Gpt 6 Sol
3.7/10Authenticated async GPT-6 Sol agent with status polling and artifact results.
Opus 5 5
3.7/10Authenticated async Opus 5.5 agent with status polling and artifact results.
Llms Check
3.7/10檢查網站 llms.txt 與 AI 爬蟲 robots.txt 設定，並自動產生 llms.txt。
Llms
3.7/10llms.txt 檢查工具：檢查網站的 llms.txt、robots 與 sitemap。台灣繁體中文 MCP 工具。
Models
3.7/10OpenAI、Claude、Gemini 模型下架日、剩餘天數與官方建議替代，可檢查程式碼裡的模型。每筆附官方來源。
Server
3.7/10Observability MCP server: query LLM cost/errors/latency & operate alerts/evals from Claude/Cursor
MCP Server
3.7/10Run TikTok cold-DM outreach from your LLM: senders, campaigns and inbox via the Hooka API.
Pch X402 MCP
3.7/10PathCourse Health inference SKUs as x402 paid MCP tools, billed per call in USDC on Base.
Hf MCP Server
3.5/10Connect to Hugging Face Hub and thousands of Gradio AI Applications
MCP Server
3.5/10Monetize and manage your Tip4Serv store directly from your LLM.
MCP Server
3.5/10MCP server that exposes the Lenderprice platform's capabilities to AI models.
Doing
3.5/10simple task manager for your LLM
Intel
3.5/10LLM provider intelligence: recommendations, pricing, and status
Gen Ai
3.5/10Generate and edit images, videos, and audio with 150+ models from 20+ vendors.
Mental Model
3.5/10Robert Blust: One model, true everywhere
Mental Model
3.5/10CompanyGraph: Written once, read by both
Mental Model
3.5/10GuestGraph: One guest, not five strangers
Authenticated Llm Agent
3.3/10Authenticated LLM Agent
Authenticated Llm Jwt Agent
3.3/10Authenticated LLM JWT Agent
Authenticated Llm MCP Agent
3.3/10Authenticated LLM MCP Agent
Authenticated Multi Llm Agent
3.3/10Authenticated Multi-LLM Agent
Encrypted Oauth Llm Agent
3.3/10Encrypted OAuth LLM Agent
Llm Orchestration Agent 2 Df5979
3.3/10LLM Orchestration Agent 2
Llm Orchestration Agent D0A1A1
3.3/10LLM Orchestration Agent
Llm Orchestration Agent MCP
3.3/10LLM Orchestration Agent (Mcp)
Llm Orchestration Jwt Agent
3.3/10LLM Orchestration JWT Agent
Llm Orchestration MCP Agent
3.3/10LLM Orchestration MCP Agent
Oauth Langchain Openai Agent
3.3/10OAuth LangChain OpenAI Agent
Oauth Multi Llm Orchestrator
3.3/10OAuth Multi-LLM Orchestrator
Traced Llm MCP Proxy
3.3/10Traced LLM MCP Proxy
Traced Llm Proxy
3.3/10Traced LLM Proxy
Traced Multi Llm Proxy
3.3/10Traced Multi-LLM Proxy
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.