经 AI Skill Hub 精选评估,MCP工具模板 获评「强烈推荐」。这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 8.0 分,适合有一定技术背景的用户使用。
MCP工具模板 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
MCP工具模板 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/AndrewAltimit/template-repo
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"mcp----": {
"command": "npx",
"args": ["-y", "template-repo"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 MCP工具模板 执行以下任务... Claude: [自动调用 MCP工具模板 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"mcp____": {
"command": "npx",
"args": ["-y", "template-repo"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
A reference architecture for AI agent orchestration, trust measurement, and tool integration. Designed to be studied, forked, and adapted -- not contributed to directly. All code changes in this repository are authored by AI agents under human oversight. Browse the project showcase for an overview.
This repo demonstrates how to run a council of AI agents (Claude, OpenCode, Crush) across a shared codebase with board-driven task delegation, automated PR review, security hardening, and containerized tooling. (OpenAI/Google integrations have been disabled -- see security notice.) It also includes standalone research packages for sleeper agent detection, autonomous economic agent simulation, and tamper-responsive hardware. Several companion repositories consume or extend the functionality of this project.
Use this repo to learn how to: - Orchestrate multiple AI agents with a GitHub Projects v2 work queue - Measure and enforce trust boundaries for autonomous agents (wrapper guards, iteration limits, claim tracking) - Integrate 20 MCP servers spanning code quality, content creation, 3D graphics, video editing, and speech synthesis - Build hardened CI/CD pipelines for agent-authored code (15-stage pipeline, security scanning, multi-arch Docker builds) - Detect sleeper agent behaviors via residual stream analysis and linear probes - Integrate AI agents into legacy software via runtime injection, shared memory IPC, and overlay rendering

---
Important: This is an advanced template designed for experienced developers working with autonomous AI agents. Before diving in, we strongly recommend: 1. Read the AI Safety Training Guide - Essential concepts for safe human-AI collaboration, including deception detection, scalable oversight, and control protocols 2. Take an AI Safety course at BlueDot Impact - Free, rigorous training programs covering AI safety fundamentals, governance, and alignment Working with AI agents introduces risks that differ fundamentally from traditional software. Understanding these risks isn't optional - it's a prerequisite for responsible development.
---
cd packages/economic_agents && cargo build --release cd tools/rust/github-agents-cli && cargo build --release cd tools/rust/board-manager && cargo build --release ```
pip install -e ./packages/sleeper_agents
For enterprise environments requiring custom certificates, customize automation/corporate-proxy/shared/scripts/install-corporate-certs.sh. This script runs during Docker builds for all containers. See the customization guide for details.
New to the template? Check out our Template Quickstart Guide for step-by-step customization instructions!
2. Clone and setup
git clone https://github.com/AndrewAltimit/template-repo
cd template-repo
# Build the Rust CLI tools (optional - pre-built binaries available in releases)
cd tools/rust/board-manager && cargo build --release
cd ../github-agents-cli && cargo build --release
3. Set API keys (if using AI features)
export OPENROUTER_API_KEY="your-key-here" # For OpenCode/Crush
.mcp.json and auto-started by Claude. See MCP Configuration for essential vs full setups.5. Run CI/CD operations
automation-cli ci run full # Full pipeline
For detailed setup, see CLAUDE.md and Template Quickstart Guide.
| Guide | Description | Source | |
|---|---|---|---|
| **Agentic Workflow Handout** | AI agent pipeline architecture and workflows | [Download](https://github.com/AndrewAltimit/template-repo/releases/latest) | [LaTeX](docs/agents/Agentic_Workflow_Handout.tex) |
| **Sleeper Agents Framework** | AI backdoor detection using residual stream analysis | [Download](https://github.com/AndrewAltimit/template-repo/releases/latest) | [LaTeX](packages/sleeper_agents/docs/Sleeper_Agents_Framework_Guide.tex) |
| **AgentCore Memory Integration** | Multi-provider AI memory system | [Download](https://github.com/AndrewAltimit/template-repo/releases/latest) | [LaTeX](docs/integrations/ai-services/AgentCore_Memory_Integration_Guide.tex) |
| **Virtual Character System** | AI agent embodiment platform | [Download](https://github.com/AndrewAltimit/template-repo/releases/latest) | [LaTeX](docs/integrations/ai-services/Virtual_Character_System_Guide.tex) |
| **AI Agent Containment & Infrastructure Security** | Isolation, trust-tiered execution, and physical security for AI agents | [Download](https://github.com/AndrewAltimit/template-repo/releases/latest) | [LaTeX](docs/hardware/latex/ai-agent-containment-infrastructure-security-framework.tex) |
| **BioForge CRISPR Automation** | Agent-driven biological automation platform | [Download](https://github.com/AndrewAltimit/template-repo/releases/latest) | [LaTeX](docs/hardware/latex/bioforge-crispr-automation.tex) |
| **Secure Terminal Briefcase** | Tamper-responsive hardware security system with PQC recovery | [Download](https://github.com/AndrewAltimit/template-repo/releases/latest) | [LaTeX](docs/hardware/latex/secure-terminal-briefcase.tex) |
.mcp.json, auto-started by ClaudeSee MCP Architecture Documentation and STDIO vs HTTP Modes for details.
See .env.example for all available options.
.mcp.json - MCP server configuration for Claude Codedocker-compose.yml - Container services configurationCLAUDE.md - Project-specific Claude Code instructions (root directory)AGENTS.md - Universal AI agent configuration and guidelines (root directory)docs/agents/project-context.md - Context for AI reviewersFor complete tool listings, see MCP Tools Reference
AI agents autonomously manage the development lifecycle from issue creation through PR merge:
Issue Created → Admin Approval → Agent Claims → PR Created → AI Review → Human Merge
The Flow:
backlog-refinement.yml, automatically added to the GitHub Projects board[Approved][Claude] (or another agent name) to authorize workboard-agent-worker.yml finds approved issues, the agent claims the issue and creates a working branchpr-validation.yml triggers AI code review (Claude + OpenRouter); pr-review-monitor.yml lets agents iterate on feedbackSecurity Model:
[Approved][Agent] comment.agents.yaml → security.agent_admins can approve[Action][Agent] format (e.g., [Approved][Claude]) to prevent false positivesSee Security Documentation for the complete security model.
Standalone packages addressing different aspects of AI agent development, safety, and security:
| Package | Purpose | Documentation | |
|---|---|---|---|
| **[Sleeper Agents](packages/sleeper_agents/)** | Research-validated detection framework for hidden backdoors in LLMs, based on Anthropic's research on deceptive AI that persists through safety training | [README](packages/sleeper_agents/README.md) \ | [PDF Guide](https://github.com/AndrewAltimit/template-repo/releases/latest) |
| **[Economic Agents](packages/economic_agents/)** | Rust-based simulation framework demonstrating autonomous AI economic capability - agents that earn money, form companies, hire sub-agents, and seek investment. For governance research and policy development | [README](packages/economic_agents/README.md) | |
| **[Tamper Briefcase](packages/tamper_briefcase/)** | Tamper-responsive Raspberry Pi briefcase with dual-sensor detection, LUKS2 cryptographic wipe, and hybrid PQC recovery USB. For secure physical transport of field-deployable agent terminals | [README](packages/tamper_briefcase/README.md) \ | [Hardware Docs](docs/hardware/secure-terminal-briefcase.md) |
Rust CLI Tools (in tools/rust/):
| Tool | Purpose | Documentation |
|---|---|---|
| **[github-agents-cli](tools/rust/github-agents-cli/)** | Issue/PR monitoring, refinement, code analysis, and agent execution | [README](tools/rust/github-agents-cli/README.md) |
| **[board-manager](tools/rust/board-manager/)** | GitHub Projects v2 board operations - claim, release, status updates | [README](tools/rust/board-manager/README.md) |
| **[git-guard](tools/rust/git-guard/)** | Git CLI wrapper requiring sudo for dangerous operations (force push, --no-verify) | [README](tools/rust/git-guard/README.md) |
| **[gh-validator](tools/rust/gh-validator/)** | GitHub CLI wrapper for automatic secret masking | [README](tools/rust/gh-validator/README.md) |
| **[pr-monitor](tools/rust/pr-monitor/)** | Dedicated PR monitoring for admin/review feedback during development | [README](tools/rust/pr-monitor/README.md) |
| **[markdown-link-checker](tools/rust/markdown-link-checker/)** | Fast concurrent markdown link validator for CI/CD pipelines | [README](tools/rust/markdown-link-checker/README.md) |
| **[code-parser](tools/rust/code-parser/)** | Parse and apply code blocks from AI agent responses | [README](tools/rust/code-parser/README.md) |
| **[mcp-code-quality](tools/mcp/mcp_code_quality/)** | Rust MCP server for code quality tools (formatting, linting, testing) | [README](tools/mcp/mcp_code_quality/README.md) |
本项目是一个面向 AI Agent 编排与安全性的参考架构模板。它集成了 AI Agent 编排、信任度测量及工具集成功能,旨在为开发者提供一个可供研究、Fork 并二次开发的基准。值得注意的是,本项目采用“AI 驱动”的开发模式,仓库中的所有代码变更均由 AI Agent 在人类监督下完成,展示了 AI 议会(Council of AI)协同工作的实际应用场景。
本项目功能强大且���块化,包含 20 个 MCP Servers,涵盖代码质量、内容创作、3D 图形、视频编辑及语音合成等领域。内置 6 个 AI Agents 可实现从 Issue 创建到 PR 合并的自主开发工作流。此外,还提供了 4 个核心 Package,包括 Sleeper Agent 检测、经济 Agent 模拟、防篡改手提箱及 CRISPR 自动化工具。整体采用 Container-First 架构,确保环境的一致性。
运行本项目需要具备 Rust 工具链以构建相关的 Rust Packages(如 economic_agents、github-agents-cli 及 board-manager)。此外,系统需支持 Python 环境以安装相关的 Python 软件包。对于容器化部署,请确保已安装 Docker (v20.10+) 及 Docker Compose (v2.0+)。
安装过程分为多个阶段:首先,需使用 Rust 工具链通过 `cargo build --release` 构建必要的 CLI 工具与 Package;其次,通过 `pip install -e` 安装 Python 相关的 Sleeper Agents 包。针对企业级环境,若需使用自定义证书,可通过 `automation/corporate-proxy` 下的脚本在 Docker 构建过程中进行配置,以适配企业内部代理环境。
初次使用的开发者请务必查阅 `docs/QUICKSTART.md` 获取分步定制指南。本项目支持两种 MCP 运行模式:STDIO Mode 用于本地 MCP,通过 `.mcp.json` 配置并由 Claude 自动启动;HTTP Mode 则通过 Docker Compose 在远程节点运行 MCP。开发者可以根据需求选择本地开发或远程容器化部署。
项目配置高度模块化。环境变量请参考 `.env.example` 文件。核心配置文件包括:`.mcp.json` 用于配置 Claude Code 的 MCP Server;`docker-compose.yml` 用于管理容器化服务;根目录下的 `CLAUDE.md` 存储项目特定的 Claude Code 指令;`AGENTS.md` 定义了通用的 AI Agent 配置与准则;`docs/agents/project-context.md` 则为 AI Reviewer 提供必要的上下文信息。
本项目提供了详尽的工具参考文档。开发者可以通过 `docs/mcp/tools.md` 查看完整的 MCP Tools 列表。此外,针对特定的 AI Code Agents、MCP Tools 以及 Gaea2 等工具,项目还提供了专门的 Quick Reference(快速参考指南),方便开发者快速检索接口与功能说明。
本项目实现了先进的 Agentic Git Workflow,实现了从 Issue 创建到合并的全自动化生命周期管理。工作流流程为:Issue 创建 → 管理员审批 → Agent 认领 → 创建 PR → AI 自动评审 → 人类最终合并。通过这种方式,AI Agent 可以自主管理开发任务,而人类开发者则专注于关键节点的决策与审���。此外,项目还包含多个独立的 Package,用于处理 AI 安全、后门检测及自动化任务。
高质量的MCP工具模板,适合代理编排与安全
该工具使用 Unlicense 协议,商用场景请仔细阅读协议条款,必要时咨询法律意见。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ Unlicense — 公共领域,完全无版权限制,可自由使用。
AI Skill Hub 点评:MCP工具模板 的核心功能完整,质量优秀。对于Claude Desktop / Claude Code 用户来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | template-repo |
| 原始描述 | 开源MCP工具:Agent orchestration & security template featuring MCP tool building, agent2agent。⭐130 · Rust |
| Topics | agent-orchestrationagent-securityai-agentsai-governancerust |
| GitHub | https://github.com/AndrewAltimit/template-repo |
| License | Unlicense |
| 语言 | Rust |
收录时间:2026-07-05 · 更新时间:2026-07-11 · License:Unlicense · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端