找到适合你的 MCP Server，快速完成接入

Agentforce Reliable Server

Reliable MCP-compliant Agentforce API server with fallback modes

agent-GitHub

GitHub AI Agent powered by official GitHub MCP Server. Uses LangGraph and LangChain MCP Adapters. Agent is exposed on various agent transport protocols (AGNTCY Slim, Google A2A, MCP Server)

Security scanner and trust verification for AI agent tools. Scans GitHub repositories for vulnerabilities and returns signed trust attestations (Ed25519/JWS) with trust-tiered rate limiting recommendations.

Adds a live git branch status bar to the Claude interface for monitoring multiple repositories simultaneously. It provides tools for managing repository tracking and visibility through natural language commands.

An MCP (Model Context Protocol) server that enables interactive debugging with code instrumentation for AI coding assistants. Inspired by Cursor's debug mode.

An MCP server that wraps OpenAI's Codex CLI to automate repository cloning and code analysis tasks. It enables users to execute complex coding requests on specific Git branches and subfolders using standardized MCP tools.

agentico-dev MCP-server

公开目录未提供摘要。

MCP server that exposes T54 x402 seller SKUs from OpenAPI as tools: contract triage, audit, and monitoring plus T54 commerce tools. HTTP 402 invoices are paid via x402_broker_client (XRPL / Base USDC depending on env); stdio for Cursor/Claude, Streamable HTTP for hosted use.

Agentic Trust

The unified MCP server platform for production AI agents. Enterprise-grade authentication, monitoring, and deployment in minutes.

Agent Identity Trust - MCP server providing AI-powered tools and automation by MEOK AI Labs

Enables users to search and discover over 500 AI agent endpoints and x402 APIs directly from MCP-compatible clients like Claude and Cursor. It provides tools to query endpoints by keyword, category, or capability while offering access to detailed provider statistics.

Agent MCP Community

agent mcp server 社区

A cloud platform for registering and using remote tools with GitHub's MCP service, enabling agents to access registered tools through SSE endpoints.

MCP server that exposes agent-memory-daemon to any MCP-compatible client — Kiro (CLI & IDE), Claude Desktop, Cursor, and others. The daemon does the thinking (consolidation + extraction); this server is a thin filesystem bridge so agents can read, append, and search memory through the Model Context Protocol.

Governed memory for coding agents with trust lifecycle, conflict detection, staleness tracking, and health scoring. SQLite + FTS5, zero infrastructure. Works with Claude Code, Cursor, Codex, Windsurf.

MCP server for AgentMinds collective intelligence platform, enabling AI agents to scan websites for security/SEO/performance issues, pull personalized recommendations, and share findings across the network.

agent-mq is a message queue that enables AI coding agents to communicate with each other across sessions and machines. Agents can send messages, delegate tasks, and coordinate work — all through MCP tools. Supports Claude Code, Cursor, Codex, OpenClaw, and any MCP-compatible tool. UUID-based authentication with per-user data isolation. Self-hostable with Docker.

Governance kernel for AI agents — policy enforcement, code safety verification, multi-model hallucination detection (CMVK), trust attestation (IATP), and immutable audit trails. Works with Claude Desktop, Cursor, and any MCP client.

Agent Pagerduty

PagerDuty AI Agent powered by 1st Party MCP Server using OpenAPI Codegen, LangGraph and LangChain MCP Adapters. Agent is exposed on various agent transport protocols (AGNTCY ACP, Google A2A, MCP Server)Agent for PagerDuty

Agent Proxmox

langchain-based client for proxmox mcp server - co-pilot experiment