无凭据 MCP 策略代理,具备细粒度能力与防篡改凭证。Secretless MCP policy proxy with scoped capabilities and tamper-evident receipts
仓库/Skill 库
471 个 · Skill/MCP
适用于代码 agent 的安全只读型服务器资源管理器:MCP 接口、RO 沙箱,docker/postgres/redis/mongo/rabbitmq 插件Безопасный readonly-эксплорер сервера для кодового агента: MCP-интерфейс, RO-песочница, плагины docker/postgres/redis/mongo/rabbitmq
Euro Truck Simulator 2 / American Truck Simulator 的遥测与驾驶分析 MCP server,附带无头 Claude 分析 agent。只读、Family-A。MCP server for Euro Truck Simulator 2 / American Truck Simulator telemetry + driving analytics, with a headless Claude analytics agent. Read-only, Family-A.
不要再重复解决同一段代码——一个本地优先的分布式推理缓存:来自真实环境的匿名兼容性证据,加上面向编码 LLM 的已验证最小示例。Stop solving the same code twice — a local-first distributed reasoning cache: anonymous compatibility evidence from real environments plus verified minimal samples for coding LLMs.
集成 ChatGPT web 与 Codex,用于 Agentic 编码工作流:ChatGPT 负责思考,Codex 负责执行,以节省 Codex 用量配额。Integrates ChatGPT web and Codex for agentic coding workflows ChatGPT thinks, Codex executes for saving Codex usage limits.
面向 Source 引擎地图工作的 MCP server:读取并检查 VMF、无重排编辑、按格式上限测算 BSP、通过 Wine(原生或 Hammer++)编译。MCP server for Source-engine map work: read and lint VMF, edit without reformatting, measure BSP against format limits, compile under Wine (stock or Hammer++)
受治理的持久化 AI worker,配备默认拒绝权限、人工审批、dry-run 以及经过认证的 MCP。Governed persistent AI workers with default-deny authority, human approvals, dry-runs, and an authenticated MCP.
AI Coding Memory MCP 2026:用于持久化 Sprint 与决策管理的 20 个工具。AI Coding Memory MCP 2026: 20 Tools for Persistent Sprint & Decision Management
基于 Base 的 fail-closed 支付安全判定:识别已知恶意钱包、高度相似 token 及反复 rug 的资方。非托管、仅依赖描述符——工具本身不转移资金。Fail-closed safe-to-pay verdicts on Base: known-bad wallets, look-alike tokens, repeat rug funders. Non-custodial, descriptor-only — no tool moves funds.
Perseus Vault 与 DeepSeek Harness 集成:MCP 配置示例 + 原生 pre-step memory-injection 插件Perseus Vault integration for DeepSeek Harness: MCP config example + native pre-step memory-injection plugin
插入到 MCP 服务器前方的安全与可信代理——策略拦截、rug-pull 检测、JIT 审批、哈希链审计。124 个测试。MCP 서버 앞에 끼어드는 보안·신뢰성 프록시 — 정책 차단, rug-pull 탐지, JIT 승인, 해시 체인 감사. 124 tests
向 Mac 上的 AI 编码 agent 展示 iOS 应用的实际运行状态——屏幕画面、应用内部状态、网络流量与日志,让检查 UI 变更不再依赖手动点击和截图循环。Shows what your iOS app is actually doing — the screen, the app's own state, its network traffic and its logs — to an AI coding agent on your Mac, so checking a UI change stops being a manual tap-and-screenshot loop.
基于 TypeScript 的独立框架,通过统一原语 Component 组合安全的个人 AI agent:manifest-first 发现、能力授予、正交模型路由与信息流控制。Standalone TypeScript framework for composing secure personal AI agents from one universal primitive — the Component. Manifest-first discovery, capability grants, orthogonal model routing, and information-flow control.
Adobe Experience Manager 的 W3C WebMCP 集成 — 通过 navigator.modelContext 让浏览器 AI agent 可发现并调用 AEM Core Components。W3C WebMCP integration for Adobe Experience Manager - makes AEM Core Components discoverable and callable by browser AI agents via navigator.modelContext
可验证混合 AI 执行的合约层 —— 研究预标准 0.36.0。A contract layer for verifiable hybrid AI execution — research pre-standard 0.36.0
为 LLM Agent 提供探索与调用任意 OpenAPI/Swagger/Postman API 能力的 MCP server,支持搜索、检查与调用。MCP server that gives LLM agents superpowers to explore and call any OpenAPI/Swagger/Postman API — search, inspect, invoke.
为 Claude 提供跨会话持久记忆——将 TriliumNext 转化为持久化、图结构化第二大脑的 MCP server。MIT 许可。Give Claude a memory that survives the conversation - an MCP server that turns TriliumNext into a persistent, graph-structured second brain. MIT.
面向真实工程师的图工程(Graph-Engineering):图定义工作流,工作流构建图。基于 mattpocock/skills。Graph-Engineering for Real Engineers: Graphs define workflows; workflows build graphs. Based on mattpocock/skills.
本地化、可复现的 Python DNA/RNA 序列工具,支持可选 MCP 访问。Local, reproducible DNA and RNA sequence utilities for Python, with optional MCP access.
Lafuanh Mind Bridge Connect 2026——无需整理的 AI 知识同步。Lafuanh Mind Bridge Connect 2026 - AI Knowledge Sync Without Sorting
为 AI agent 提供持久且安全约束的浏览器控制——使用语义化 CLI 替代 Playwright 脚本或屏幕坐标。通过统一接口,背后使用 macOS WKWebView 与 Linux ChromiumPersistent, safety-enforced browser control for AI agents — semantic CLI instead of Playwright scripts or screen coordinates. macOS WKWebView + Linux Chromium behind one contract.
个人知识图谱:抽取、验证阶梯、检索与衰减,通过 MCP 服务任意客户端A personal knowledge graph: extraction, a verification ladder, retrieval, and decay — served over MCP to any client
2026 自主 AI Agent 平台 🚀——基于 MCP 与 DAG 的多 Agent SaaSAutonomous AI Agent Platform 2026 🚀 - Multi-Agent SaaS with MCP & DAG
Claude AI 2026 Machines 插件 - 官方 GitHub 集成指南。Machines Plugin for Claude AI 2026 - Official GitHub Integration Guide
40 项检查的设计契约验证引擎 — 为任意 URL 评分,把控 CI,强制执行 DTCG 2025.10 tokens。MCP server + GitHub Action + stylelint plugin + CLI。40-check design contract verification engine — score any URL, gate your CI, enforce DTCG 2025.10 tokens. MCP server + GitHub Action + stylelint plugin + CLI.
Give pure-text LLM agents eyes: zero-dependency image understanding, OCR & image Q&A via MCP server + standalone Python script. 给纯文本 AI Agent 的图片理解能力(看图/OCR/图片问答)。
本地 CLI,用于发现本地网络上的影子 MCP 服务器并审计认证状态。零遥测,纯本地。Local CLI to discover shadow MCP servers on your local network & audit authentication status. Zero telemetry, local-only.
Linux 上的便携 GrokBuild overlay:18 个 skill、路由、MCP、hooks、Refero/Motionsites 设计库,以及可选的本地 Design Intelligence 目录。当前版本:v1.3.1。Portable GrokBuild overlay for Linux: 18 skills, routing, MCP, hooks, Refero/Motionsites design bank, and optional local Design Intelligence catalog. Current: v1.3.1.
Measured by Nova:本地空间重建 MCP server,用于构建物理上精确的 Blender 模型。Measured by Nova: local spatial reconstruction MCP server for physically accurate Blender models.
Kosli API 的 MCP server——由目录驱动,兼容 Claude Code、Claude Desktop 及任意 MCP 客户端。MCP server for the Kosli API - catalog-driven, works with Claude Code, Claude Desktop, and any MCP client.
对接日本 gBizINFO 企业信息 REST API v2 的 MCP serverMCP server for Japan’s gBizINFO corporate information REST API v2.
用于搜索与检索日本官方 e-Stat 政府统计数据的 MCP serverMCP server for searching and retrieving Japan’s official e-Stat government statistics.
多 Agent 开发的可调度性编译器 —— 观察真实代码边界、重构冲突接缝、重新编译计划以实现并行执行。Schedulability compiler for multi-agent development — observe real code boundaries, refactor the conflicting seam, recompile the plan for parallel execution
Kiki — 一个面向 Google Campaign Manager 360 的开源对话式 trafficking 助手。集成 70 个 CM360 工具,具备写入安全确认、内置 QA 以及零凭证 MCP demo。Kiki — an open-source conversational trafficking assistant for Google Campaign Manager 360. 70 CM360 tools, write-safety confirmation, built-in QA, zero-credential MCP demo.