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
3.9/10run any ai model. compose agents, stack knowledge, connect tools. one api, pay per run.
MCP Server
3.9/10Provides capabilities that let LLM agents perform a range of infrastructure management tasks.
MCP Server
3.9/10Build zero-shot video models for object detection, and category and attribute classification.
Cannon Studio
3.9/10Public Cannon Studio MCP for product, pricing, workflow, model, and API answers.
Districts
3.9/10K-12 school district data for all 50 US states. Enrollment, demographics, and academics.
Synthesis
3.9/10kenoodl surfaces the hidden pattern the model can't reach on its own. Call when reasoning loops.
MCP Server
3.9/10Live vehicle warranty (service contract) quotes by VIN, plate, or make/model/year.
Hyperliquid Data
3.9/10Hyperliquid perp market data for LLMs: OHLCV, funding, open interest, positioning & forecasts.
Tenzro
3.9/10Tenzro Network MCP server: wallet, identity, payments, inference, staking, bridges, verification.
Lamina
3.9/10On-brand product photos, model try-ons, video reels & banners from a brief + brand kit.
Sourcing
3.9/10Agent-native supply network for components, fabrication, industrial RFQs, offers, and fulfillment.
Version Truth
3.9/10Latest versions, LTS windows, and EOL dates for 300+ products. Fresh ground truth for stale models.
Insurance Ai Regulation
3.9/10NAIC AI model bulletin adoption by state, with citations. Insurance AI compliance data.
Qwen MCP
3.9/10Pay-per-call GLM 5.3 MCP tool via x402 on Base. Reasoning, tool-calls, OpenAI-compatible.
Agent Data
3.9/10Live rankings and pricing for 10,000+ AI products and LLMs. Free tier; paid data via x402.
Titan
3.9/10GPU compute API: LLM inference (ornith-1.5) on RTX 4080, pay-per-credit in Bitcoin.
Gateway
3.9/10One MCP endpoint for 17 top Chinese LLMs. OpenAI-compatible. Up to 60% cheaper than OpenRouter.
Flatland
3.9/10Financial reasoning infrastructure for AI agents: typed models, deterministic compilation, receipts
MCP Server
3.9/10Web scraping, inference, DNS, monitoring from residential IPs — pay per request in USDC
MCP Server
3.9/10Test whether 3D assets survive Apple Quick Look and Safari , then fix what fails
Jsonshim
3.9/10Recovers malformed LLM JSON. MCP build: 218/300 on MALFORMED-300 (library build 282/300).
Audio Llm
3.9/10Discover voices and prices; buy narration, transcription and LLM text with capped USDC payments.
MCP Server
3.9/10EU-hosted AI platform: OpenAI-compatible LLM gateway, document extraction, transcription, agents.
Nces Education
3.7/10School enrollment, graduation rates, demographics, finance, and Title I data
Investigation Game
3.7/10Find out who killed Claude by interrogating the LLM driven suspects...
Time S Up
3.7/10Skybridge Example App showcasing a Time's up game with the LLM
Talarion
3.7/10A knowledge base of verified, dated facts your LLM would otherwise get wrong.
Latin
3.7/10Grounds LLMs in real Latin: Wiktionary lemmas, Morpheus inflections, citations.
Claude News
3.7/10Real-time Claude & Anthropic news from your own Claude — free, no API key.
MCP Server
3.7/10LLM routing and A-share market phase signals via LG framework.
Bardo
3.7/10Identity & continuity for AI agents, gated by a proof-of-being-an-LLM puzzle.
Latgalian
3.7/10Grounds LLMs in real Latgalian: Wiktionary lemmas, inflections, romanization.
MCP Server
3.7/10Create images & video from any MCP agent — 17 models, spend limits, one URL.
Printonic
3.7/10Print-on-demand catalog, listings, and fulfillment for AI agents.
MCP Server
3.7/10Prepaid inference for agents over hosted MCP. Chat, image, and video.
Authenticated Llm Agent Bcrypt
3.7/10Authenticated LLM Agent (Bcrypt)
Authenticated Llm Traced Agent
3.7/10Authenticated LLM Traced Agent
Authenticated MCP Agent Openai
3.7/10Authenticated MCP Agent (Openai)
Llm Observability Orchestration
3.7/10LLM Observability & Orchestration Agent
Llm Observability Orchestration Agent Langchain
3.7/10LLM Observability & Orchestration Agent (Langchain)
Llm Observability Orchestration Agent Langchain Community
3.7/10LLM Observability & Orchestration Agent (LangChain Community)
Llm Orchestration Agent 2
3.7/10MCP-Native LLM Orchestration Agent
Llm Orchestration Agent Cryptography
3.7/10LLM Orchestration Agent (Cryptography)
Llm Orchestration Agent D2Feb0
3.7/10LangSmith-Traced LLM Orchestration Agent
Llm Orchestration Agent Langchain
3.7/10LLM Orchestration Agent (Langchain)
Llm Orchestration Agent Langchain Anthropic
3.7/10LLM Orchestration Agent (Langchain Anthropic)
Llm Orchestration Agent Langchain Core
3.7/10LLM Orchestration Agent (Langchain Core)
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.