MCP 服务器目录
共收录 7539 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。
MolTrust MCP Server
AI与LLMGive an agent a verifiable identity, and check another agent's before dealing with it.
CommitLore
AI与LLMGit-native decision memory for coding agents: only the decisions still in force for the edited path
stockmatrix-mcp
AI与LLMKorean stock market theme lifecycle analysis (TLI) — rankings, stock lookup, predictions & prompts
MemoCat — Shared AI Memory
AI与LLMOne shared, persistent memory across AI agents and systems, with semantic recall and live updates.
Montycat MCP - Shared Memory for AI Agents
AI与LLMShared, persistent memory for AI agents, with semantic recall and live updates.
cartography-mcp-server
AI与LLMHuman-curated crypto market intelligence with x402 payments. Weekly signals and analysis.
CTFd
AI与LLMMCP server for CTFd v3: list challenges, submit flags, and query scoreboards via AI agents.
flipcoin
AI与LLMAgent-first prediction markets on Base. Trade, quote, create markets via MCP.
Staats
AI与LLMCookieless web analytics your coding agent reads: traffic answers, deploy impact, what broke.
rugcheck-ai
AI与LLMSolana token safety for AI agents — rug-pull, honeypot & Token-2022 trap detection before you buy.
SiteHelm
AI与LLMLet an AI agent run your WordPress site: every write previewed, verified and reversible.
agentcast
AI与LLMStructured-output enforcer: extract and validate JSON from messy LLM text.
agentfit
AI与LLMToken-aware message truncation: fit a chat history into your model's context budget.
agentguard
AI与LLMNetwork-egress firewall for agent tools: check URLs against a declarative policy.
agentsnap
AI与LLMSnapshot tests for AI tool-call traces: diff, validate, and catch silent regressions.
agentvet
AI与LLMValidate tool-call args before execution. Returns LLM-friendly retry hints.
citecite-mcp
AI与LLMInject, parse, and strip [N] citation markers in RAG outputs.
promptbudget-mcp
AI与LLMToken-budget-aware text handling: count, truncate, and chunk for LLM prompts.
agent-memory
AI与LLMPersistent, agent-owned memory with encrypted storage and shared knowledge commons.
materialmodel
AI与LLMExplore discoveries, ask questions, share findings, and build collaborations with other agents.
Yagami AI Context Firewall
AI与LLMOpen-source AI context firewall for governed model, retrieval, memory, and tool access.
smartmemory
AI与LLMNeuro-symbolic memory for LLMs (POC)
FatturaPA / SDI
AI与LLMItalian e-invoicing (FatturaPA/SDI): parse invoices, detect anomalies, VAT checks via VIES, reports.
Compartment
AI与LLMDurable agentic memory, encrypted at rest. Fully offline: no network, no API key, no cloud.