Create Hooks: Create new webhooks or MQTTHOOKS directly from your agent. List Hooks: Retrieve a list of your configured webhooks. Inspect Events: View
A local text-to-image generation server that enables AI agents to generate images, manage models, and browse history using the Z-Image-Turbo model. It supports hardware acceleration across NVIDIA, Apple Silicon, and AMD GPUs via multiple MCP transport protocols.
Self-hosted, zero-knowledge encrypted, self-destructing secrets for secure agent-to-agent coordination
A multi-agent orchestration platform for Claude Code providing 61 tools for autonomous agent coordination, browser automation, and documentation intelligence. It features LanceDB-powered semantic search, knowledge graph memory systems, and advanced task management for complex development workflows.
An MCP server that connects AI assistants to the ZONT heating system via the official REST API. It enables users to monitor device states, control heating modes, and perform diagnostics using natural language.
An MCP Server that enables interaction with Zoom's API through the Multi-Agent Conversation Protocol, allowing users to access and control Zoom's functionality via natural language commands.
An MCP (Multi-Agent Conversation Protocol) Server that enables interaction with the Zoom API through natural language commands, auto-generated using AG2's MCP builder.
Negotiation math engine for AI agents. Computes Pareto frontiers, generates iso-utility counteroffers, and infers counterpart priorities. 9 tools for any multi-issue negotiation. Zero LLM tokens — pure MILP optimization.
Enables AI agents to manage zrok tunnels, shares, and access programmatically through environment management, share creation/deletion/listing, and access control actions.
A 7-layer security system for AI agents that detects and blocks prompt injection, data exfiltration, and malicious tool calls. It enables real-time scanning of inputs, outputs, and tool definitions to protect agentic workflows from emerging AI-specific threats.
Mastra支持模型上下文协议(MCP),作为连接AI代理与外部工具和资源的开放标准,提供通用的插件系统。
工具数量
0
GitHub Stars
24k
基于ComfyUI的LLM工作流构建工具,支持多种LLM模型调用和集成,适用于AI助手构建、知识库管理及多模态工作流开发。
工具数量
0
GitHub Stars
2.2k
Claude代码插件集是一个轻量级包,允许用户自定义和共享Claude代码设置,包括自定义快捷命令、专用开发任务代理、工具和数据源集成以及行为修改扩展。
工具数量
0
GitHub Stars
786
Tool UI是一个用于在AI聊天界面中渲染工具调用的React组件库,提供交互式UI组件如审批、表单、表格、图表和媒体卡片等。
工具数量
0
GitHub Stars
681
A2A(Agent2Agent)是一种开放协议,使来自不同供应商/框架的AI代理能够安全地通信和协作完成任务,打破孤立代理系统之间的壁垒,实现更复杂的跨应用自动化。
工具数量
0
GitHub Stars
592
monday.com MCP是一个开放框架,用于将AI代理集成到工作操作系统中,提供安全访问结构化数据、执行操作的工具以及做出智能决策所需的上下文。
工具数量
17
GitHub Stars
403
提供AI代理通过PHP执行和文件系统操作完全访问WordPress的服务
工具数量
0
GitHub Stars
307
一个允许AI助手通过Discord向人类提问的MCP服务器,用于需要人类输入或判断的场景。
工具数量
0
GitHub Stars
224
HeyClaude是一个社区构建的Claude目录和可浏览的注册表,包含385+个文件支持的条目,涵盖代理、MCP服务器、工具、技能等。
工具数量
0
GitHub Stars
218
基于xiaohongshu-mcp的Agent Skills集合,为小红书提供完整的自动化操作能力,包括登录管理、内容发布、搜索浏览和互动操作等功能。
工具数量
8
GitHub Stars
208









