仓库/Skill 库

1С:Enterprise 的 MCP server——AI 助手读取你的配置并生成准确的 BSL 代码。单一二进制、零依赖、11 个工具。MCP server for 1С:Enterprise — AI assistant sees your configuration and generates accurate BSL code. One binary, zero dependencies, 11 tools.

完整 Zabbix API 的 MCP server —— 237 个工具，支持多服务器、OAuth 2.1 + bearer 认证、PDF 报告，systemd 就绪。可与 ChatGPT、Claude、VS Code、Codex、JetBrains 及任何 MCP 客户端配合使用。MCP server for the complete Zabbix API - 237 tools, multi-server, OAuth 2.1 + bearer auth, PDF reports, systemd ready. Works with ChatGPT, Claude, VS Code, Codex, JetBrains and any MCP client.

面向组织级 Agent 的开源控制平面与运行时：共享公司上下文、隔离执行、审批流与 MCP。Open-source control plane and runtime for organisational agents: shared company context, isolated execution, approvals and MCP.

Opptrix——AI 驱动的全球多市场投研工作台 | 面向中国 A 股的开源 LLM 投研助手。170+ MCP 工具、因子筛选、回测、自选股与 Electron 桌面端。TypeScript · React · Fastify monorepo。Opptrix — AI驱动的全球多市场投研工作台 | Open-source LLM research assistant for China A-shares. 170+ MCP tools, factor screening, backtest, watchlist & Electron desktop. TypeScript · React · Fastify monorepo.

面向自主 agent 的企业级 gateway，提供身份管理、按通道隔离、凭据 vault、按会话防篡改审计日志。The enterprise gateway for autonomous agents. Identity management, per-channel isolation, credential vault, per-session tamper-evident audit log.

Salesforce MCP ServerSalesforce MCP Server

面向 user-aware Agent 的开源记忆与上下文方案：作用域化记忆、来源追溯、检索质量、纠错、边界、评测，以及 MCP/HTTP 访问能力。Open-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.

Pragmatic AI Labs MCP Agent Toolkit —— 一个 MCP Server，用于让 Agent 编程更加确定性Pragmatic AI Labs MCP Agent Toolkit - An MCP Server designed to make code with agents more deterministic

开源（Apache-2.0）面向建筑与地板行业的 PDF takeoff——首个由 AI agent 原生通过 MCP 驱动、而非后挂的引擎。沿墙面量房、符号扫描、带完整 provenance 的材料与用量，面向 preconstruction 场景，完全在浏览器中运行。Open-source (Apache-2.0) PDF takeoff for construction & flooring — the first engine an AI agent drives natively over MCP, not bolted on. Rooms measured on the wall faces, symbol sweeps, materials + quantities with full provenance, built for preconstruction. Runs entirely in your browser.

Blender 的 MCP server，提供 186 个建模、材质、渲染等工具，可由 Claude、Cursor、Codex、Ollama、llama.cpp 或任意 MCP client 驱动MCP server for Blender. 186 tools for modelling, materials, rendering and more, driven by Claude, Cursor, Codex, Ollama, llama.cpp, or any MCP client.

提供全面 Microsoft Teams 和 Graph API 访问的 MCP server，支持 AI assistant 的消息、搜索与用户管理等功能。MCP server providing comprehensive Microsoft Teams and Graph API access for AI assistants including messaging, search, and user management.

Wanaku MCP RouterWanaku MCP Router

Smart Promise Tracker AI 2026 —— 承诺 Memory 引擎。Smart Promise Tracker AI 2026 – Commit Memory Engine

自动化你的工作：local-first AI 任务中枢。Email、Teams、Slack 及报告 → 统一时间线 → AI 分类 → 你的编码 agent（Claude Code、Codex、Gemini）执行，你审批。Automate your job: local-first AI task hub. Email, Teams, Slack & reports -> one timeline -> AI triage -> your coding agents (Claude Code, Codex, Gemini) do the work, you approve.

本地 MCP server，用于有状态、fail-closed 的 Logic Pro 控制与项目实时回读。Local MCP server for stateful, fail-closed Logic Pro control and live project readback.

KiCad 的 MCP 服务器，将 AI Agent 接入原理图与 PCB 工作流，支持 ERC/DRC 校验、DFM 检查、BOM 分析与制造准备 —— 配备受控编辑与人工把关的发布工作流。MCP server for KiCad, connecting AI agents to schematic and PCB workflows, ERC/DRC validation, DFM checks, BOM analysis, and manufacturing preparation—with controlled edits and human-gated release workflows.

通过迭代实现自我改进的 AgentSelf improving agents through iterations

面向 Cursor 2026 的开源 AI Expert Agent Bridge。Open Source AI Expert Agent Bridge for Cursor 2026

运行一组协同 agent，聚焦于特定目标。Run a hive mind of agents to focus on a specific goal

面向 AI Agent 的代码搜索工具：32 个 MCP 工具，SQLite 索引，单一二进制文件零依赖。可解析 1С:Предприятие — Конфигуратор 与 EDT 的导出文件；8.8 万文件的配置库索引耗时 6 分钟，查询响应 10 毫秒。Code 索引 MCP server：基于 tree-sitter AST，支持 14 种语言，20 个通用工具 + 12 个 1C/BSL 专用工具。Поиск по коду для ИИ-агентов: 32 инструмента MCP, индекс на SQLite, один бинарник без зависимостей. Разбирает выгрузки 1С:Предприятие — Конфигуратор и EDT; конфигурация на 88 тыс. файлов индексируется за 6 минут, ответ на запрос — 10 мс. Code index MCP server: tree-sitter AST for 14 languages, 20 universal tools + 12 for 1C/BSL.

Harness 官方 MCP Server。Harness’ official MCP Server

面向 agentic AI 与受治理分析的源代码可用的语义与上下文层、规则引擎和语义 sidecar；可将声明式 YAML 模型编译为优化的 SQL、KPI 和语义上下文，覆盖 8 种 SQL 方言Source-available semantic and context layer, rule engine, and semantic sidecar for agentic AI and governed analytics. Compiles declarative YAML models into optimized SQL, KPIs, and semantic context across 8 SQL dialects.

基于 Google ADK 构建的生产级多 Agent 编排引擎：数据库驱动的 Agent 配置、支持 50+ LLM provider、MCP 协议、持久化记忆、Web 仪表盘与 RBAC。Production-ready multi-agent orchestration engine built on Google ADK. Database-driven agent config, 50+ LLM providers, MCP protocol, persistent memory, web dashboard, RBAC.

驱动真实 Chrome 与已登录会话的 MCP 服务器 — 真实指纹（通过 bot.sannysoft 检测）、拟人化输入、识别反爬机制。共 43 个工具，打包为单一静态 Rust 二进制MCP server that drives real Chrome with your real logged-in sessions — genuine fingerprint (passes bot.sannysoft), human-like input, bot-wall aware. 43 tools, single static Rust binary.

开源代码化动画架构图。Diagram-native DSL、17 种布局引擎、Web Animations API，以及面向 AI Agent 的 MCP server。🎬 Open-source animated architecture diagrams as code. Diagram-native DSL, 17 layout engines, Web Animations API, and MCP server for AI agents.

面向个人的本地多 Agent 协同工作空间。与拥有独立身份与持久记忆的 AI 队友深度协作：频道分工、任务指派、无限矢量画布与原生 MCP。A local-first multi-agent collaborative workspace.

用于全栈 LLM 驱动渗透测试的 cybersecurity harness，可自主发现并修复漏洞，7×24 小时不间断。[RESEARCH PREVIEW]A cybersecurity harness for full-stack LLM-driven penetration testing. Find and fix vulnerabilities autonomously, 24/7. [RESEARCH PREVIEW]

面向 ComfyUI 的本地优先侧边栏 AI Agent——运行在你自己的 Claude 或 ChatGPT 订阅上（无需 API key，不产生额外 LLM 成本）。通过自然语言驱动你的实时图：编辑、工作流与安装。作为 comfyui-mcp 的面板 UI，comfyui-mcp 是 ComfyUI 的 Agent 原生控制平面。The local-first sidebar AI agent for ComfyUI — runs on your own Claude OR ChatGPT subscription (no API keys, no extra LLM costs). Drives your live graph: edits, workflows & installs in natural language. The panel UI for comfyui-mcp, the agent-native control plane for ComfyUI.

以 Agent 优先的 DeepSeek Harness 手册：提供源可溯的运行时、插件、MCP、沙箱、评测、排障、多语言以及 Awesome 生态指南。Agent-first DeepSeek Harness handbook: source-backed runtime, plugin, MCP, sandbox, evaluation, troubleshooting, multilingual, and Awesome ecosystem guides.

OpenRouter 的 MCP server——与 300+ LLM（Claude、Gemini、GPT）对话，分析图像/音频/视频，生成图像/语音/音乐/视频（Veo 3.1、Sora、Seedance、Wan），支持 Claude Desktop、Cursor、Kiro、VS CodeMCP server for OpenRouter — chat with 300+ LLMs (Claude, Gemini, GPT), analyze images / audio / video, generate images / speech / music / video (Veo 3.1, Sora, Seedance, Wan) from Claude Desktop, Cursor, Kiro, VS Code.

为 AI 编程 Agent 提供本地语义代码智能、项目记忆与工作流上下文。Local semantic code intelligence, project memory, and workflow context for AI coding agents.

开源 AI 可见性平台 — 跨 ChatGPT、Claude、Gemini、Google AI Overviews、Google AI Mode、Perplexity、Grok 和 Copilot 跟踪 AI 可见性、引用、提示、竞争对手与内容机会。Open-source AI Visibility Platform — track AI visibility, citations, prompts, competitors, and content opportunities across ChatGPT, Claude, Gemini, Google AI Overviews, Google AI Mode, Perplexity, Grok, and Copilot.

面向安全关键型控制系统的 Agent 接口与安全防护框架。An agentic interface and safety harness for safety-critical control systems

Perseus Vault — 面向 AI agent 的持久化、加密、时序感知记忆。单个 Rust 二进制、单文件、local-first、原生支持 MCP，MIT 许可。Perseus Vault — durable, encrypted, time-aware memory for AI agents. One Rust binary, one file, local-first, MCP-native, MIT.

跨境电商 AI 知识库，面向人类阅读、面向 Agent 安装。包含 69 篇三语指南、878 条结构化提示、94 个实体 / 318 条约束的领域本体，以及通过 MCP 提供的 9 个 Agent Skill。事实性陈述标注日期并经 CI 校验；提示声明其数据需求与失效边界。CC0 许可。Cross-border e-commerce AI knowledge base, designed to be read by people and installed by agents. 69 trilingual guides, 878 structured prompts, a 94-entity / 318-constraint domain ontology, and 9 agent skills served over MCP. Factual claims are dated and CI-verified; prompts declare their data requirements and failure boundaries. CC0.

为 Claude Code、Codex、Pi、OMP 及远程 MCP 客户端提供上下文高效的项目搜索与有界代码分析，基于 ripgrep，支持稳定游标、源码检视与结构化证据。Context-efficient project search and bounded code analysis for Claude Code & Codex & Pi & OMP. and remote MCP clients, powered by ripgrep with stable cursors, source inspection, and structural evidence.