MCP 服务器目录
共收录 7330 个 MCP(Model Context Protocol)服务器,给 AI Agent 接上浏览器、数据库、搜索等工具能力。
Eval Engine API
AI与LLMPay-per-call AI evaluation MCP server. Score LLM outputs against benchmark rubrics via Workers AI.
sovereign-engine
AI与LLM15 paid AI agent primitives via x402 (USDC on Base). Pay-per-call MCP server.
AbaPay
AI与LLMNon-custodial stablecoin bill-pay rails on Celo & Base for AI agents, settled on-chain via MCP.
invigil
AI与LLMLinters check your code. Invigil checks whether your repo is legible — to newcomers and AI agents.
Obolus
AI与LLMDisposable Algorand wallet for AI agents. Pay x402 resources in USDC, no human provisioning.
CLIO Arxiv
AI与LLMArXiv MCP server implementation using Model Context Protocol
CLIO Chronolog
AI与LLMChronoLog MCP server implementation using Model Context Protocol
CLIO Compression
AI与LLMCompression MCP server implementation using Model Context Protocol
CLIO Hdf5
AI与LLMHDF5 FastMCP - Scientific Data Access for AI Agents | CLIO Kit MCP Server
CLIO Lmod
AI与LLMLmod MCP - Environment Module Management for LLMs with comprehensive module operations
CLIO Node Hardware
AI与LLMNode Hardware MCP - Comprehensive Hardware Monitoring and System Analysis for LLMs with...
CLIO Pandas
AI与LLMPandas MCP - Advanced Data Analysis for LLMs with comprehensive pandas operations
CLIO Parallel Sort
AI与LLMParallel Sort MCP - High-Performance Log File Processing for LLMs with advanced sorting and analysis
CLIO Scientific Catalog
AI与LLMOperator-owned scientific dataset discovery for remote agents
CLIO Spack
AI与LLMStructured Spack discovery and installation tools for scientific agents
agent-guard
AI与LLMSafety checks an agent runs before it acts: package malware, destructive command, secret leak.
evalgate
AI与LLMStatistical checks an agent runs before trusting an AI eval number (is #1 real, judge bias, more).
numguard
AI与LLMVerify a number before an agent asserts it — evals, backtests (Deflated Sharpe), signed receipts.
Agent Memory MCP
AI与LLMMemory, docs, and repo context layer for engineering agents.
Iris
AI与LLMStop shipping agents on vibes. Score every agent output for quality, safety, and cost.
MemoryGuard
AI与LLMLocal-first governed MCP memory backend for coding agents.
mcp
AI与LLMRead-only Hyperliquid data for AI agents: fills, candles, funding, liquidations, wallet analytics.
secret-safe-env
AI与LLMWrite secrets into .env without the agent ever seeing the value - Windows masked dialog (繁中 UI)
forage
AI与LLMSelf-improving tool discovery for AI agents. Find, install, and use new MCP servers automatically.