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LLM

Give an agent a verifiable identity, and check another agent's before dealing with it.

v1.2.4 MoltyCel/moltrust-mcp-server

CommitLore

AI与LLM

Git-native decision memory for coding agents: only the decisions still in force for the edited path

v1.2.0 MongLong0214/commitlore

stockmatrix-mcp

AI与LLM

Korean stock market theme lifecycle analysis (TLI) — rankings, stock lookup, predictions & prompts

v0.5.0 MongLong0214/stock-ai-newsletter

MemoCat — Shared AI Memory

AI与LLM

One shared, persistent memory across AI agents and systems, with semantic recall and live updates.

v0.4.3 MontyGovernance/memocat-mcp

Montycat MCP - Shared Memory for AI Agents

AI与LLM

Shared, persistent memory for AI agents, with semantic recall and live updates.

v1.1.6 MontyGovernance/montycat-mcp

cartography-mcp-server

AI与LLM

Human-curated crypto market intelligence with x402 payments. Weekly signals and analysis.

v1.2.0 MrCartographer/cartography

CTFd

AI与LLM

MCP server for CTFd v3: list challenges, submit flags, and query scoreboards via AI agents.

v1.0.4 MrJamescot/ctfd-mcp-server

flipcoin

AI与LLM

Agent-first prediction markets on Base. Trade, quote, create markets via MCP.

v0.1.2 flipcoin-fun/flipcoin-mcp

Staats

AI与LLM

Cookieless web analytics your coding agent reads: traffic answers, deploy impact, what broke.

v1.0.1 MrViolets/staats-mcp

rugcheck-ai

AI与LLM

Solana token safety for AI agents — rug-pull, honeypot & Token-2022 trap detection before you buy.

v1.2.0 MrWizardlyLoaf/rugcheck-ai

SiteHelm

AI与LLM

Let an AI agent run your WordPress site: every write previewed, verified and reversible.

v0.16.0 Mrshahidali420/SiteHelm

agentcast

AI与LLM

Structured-output enforcer: extract and validate JSON from messy LLM text.

v0.1.0 MukundaKatta/agentcast-mcp

agentfit

AI与LLM

Token-aware message truncation: fit a chat history into your model's context budget.

v0.1.0 MukundaKatta/agentfit-mcp

agentguard

AI与LLM

Network-egress firewall for agent tools: check URLs against a declarative policy.

v0.1.0 MukundaKatta/agentguard-mcp

agentsnap

AI与LLM

Snapshot tests for AI tool-call traces: diff, validate, and catch silent regressions.

v0.1.0 MukundaKatta/agentsnap-mcp

agentvet

AI与LLM

Validate tool-call args before execution. Returns LLM-friendly retry hints.

v0.1.0 MukundaKatta/agentvet-mcp

citecite-mcp

AI与LLM

Inject, parse, and strip [N] citation markers in RAG outputs.

v0.1.1 MukundaKatta/mcp-stack

promptbudget-mcp

AI与LLM

Token-budget-aware text handling: count, truncate, and chunk for LLM prompts.

v0.2.0 MukundaKatta/mcp-stack

agent-memory

AI与LLM

Persistent, agent-owned memory with encrypted storage and shared knowledge commons.

v0.1.0 MastadoonPrime/agent-memory

materialmodel

AI与LLM

Explore discoveries, ask questions, share findings, and build collaborations with other agents.

v0.4.0 MaterialModel/materialmodel-integrations

Yagami AI Context Firewall

AI与LLM

Open-source AI context firewall for governed model, retrieval, memory, and tool access.

v0.8.3 MatthewTracy/yagami

smartmemory

AI与LLM

Neuro-symbolic memory for LLMs (POC)

v1.0.1 MauriceIsrael/SmartMemory

FatturaPA / SDI

AI与LLM

Italian e-invoicing (FatturaPA/SDI): parse invoices, detect anomalies, VAT checks via VIES, reports.

v0.3.2 MaurizioLisanti/fatturapa-mcp-server

Compartment

AI与LLM

Durable agentic memory, encrypted at rest. Fully offline: no network, no API key, no cloud.

v4.11.0 MaxFreedomPollard/Compartment