MCP 服务器目录
共收录 7303 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。
Tapo MCP
AI与LLMMCP server for discovering and controlling TP-Link Tapo smart home devices via AI Agents
brainllm
AI与LLMSelf-hosted memory for LLMs in TriliumNext, structured by the server and editable by you.
Flottix
AI与LLMDeterministic IT asset registry operated by AI agents over MCP. Agents propose, humans approve.
unifi-mcp
AI与LLMMCP server for Ubiquiti UniFi Network and Protect. 63 tools, 16 agent skills.
stocksense
AI与LLMFinancial data for AI agents: SEC filings, price history, insider trades, and more.
TubePull
AI与LLMDownload YouTube, TikTok, Vimeo, SoundCloud and 6 more platforms from any MCP AI chatbot.
agent-link
AI与LLMBidirectional AI agent collaboration — spawn and communicate with any agent CLI
agent-loop-mcp
AI与LLMAgentic memory manager. Install Skill: npx skills add meharajM/agent-loop-mcp
whatsapp-mcp
AI与LLMWhatsApp MCP Server - Human-in-the-loop for AI agents via WhatsApp
API Key Case
AI与LLMLocal MCP tools for secret status and guarded deployment. Values never reach the agent.
verity-mcp
AI与LLMFail-closed verify-before-you-act gate for AI agents. Signed receipts. Pay-per-call via x402.
Context Engine
AI与LLMCompress logs, retrieval chunks, and code context into structured LLM-ready signal.
relayzero
AI与LLMAgent economy on Solana — USDC via x402. Ships a BuyerAgent SDK + relayzero pay CLI.
zero-core-budget
AI与LLMAgent spending mgmt, budget tracking, ROI. Zero Core Budget.
zero-core-verify
AI与LLMPost-tx outcome verification via LLM-as-judge. Zero Core Verify.
Memento
AI与LLMHosted MCP memory for coding agents: persistent across sessions, editable markdown, team sharing.
memi
AI与LLMMemi is the design layer for agentic AI.
Brainy
AI与LLMShared knowledge base + task queue so Claude, ChatGPT and other agents can work together safely.
Memwyre
AI与LLMUniversal persistent memory and knowledge retrieval layer for AI agents and LLMs.
tnt-house-risk-data-api
AI与LLMRiskDataApi — Solana token risk scoring for AI agents. Safety score, insider clusters, honeypot.
nMEMORY
AI与LLMMemory your agent can trust — every answer carries its source; when it doesn't know, it says so.
Sprout MCP
AI与LLMModel-tiered content pipeline — cheap models seed, expensive models verify
Varyntiq
AI与LLMPre-payment checks for AI agents: x402 quotes, untrusted prompts and audit receipts.
mercury-x402-mcp
AI与LLMAgent-payable web data over x402: 18 keyless services an agent pays per call.