safe-agent-mcp
Enables any MCP client to execute DeepSeek Harness agents and shell commands through standard MCP tools, bridging multi-agent capabilities with sandboxed execution.
README
safe-agent-mcp
基于 DeepSeek Harness 的安全多 Agent MCP 网关:把 DSH 的 agent 执行能力封装成标准 MCP 工具,让任何 MCP 客户端(Claude Desktop、Cursor 等)都能调用。
这个项目解决什么
- DSH 是多 Agent 框架,但能力只能在自己的界面里用;
- MCP 是标准协议,任何客户端都能接,但本身没有 agent 能力;
- safe-agent-mcp 是两者的桥:一个 MCP 服务器,对外提供标准工具,对内驱动 DSH 的 agent(含子 Agent、沙箱)。
特性
| 关键词 | 实现 |
|---|---|
| MCP | 标准 MCP 服务器(@modelcontextprotocol/sdk),任何 MCP 客户端即插即用 |
| 多 Agent | (规划中 v1.1)通过 dsh --profile headless 驱动 DSH 子 Agent 执行任务 |
| 沙箱/安全 | (规划中 v1.2)危险命令拦截、密钥脱敏、审计日志、超时与并发限制 |
快速开始
npm install
npm run smoke # 自动化冒烟测试(协议握手 + 工具调用)
npm run inspect # 打开 MCP Inspector 可视化调试
当前已实现工具:
run_command:在沙箱中执行一条 shell 命令,返回 stdout / stderr / 退出码(Windows 下已处理 cmd 的 GBK 编码问题)。
目录结构
src/index.ts # MCP 服务器入口
tests/smoke.mjs # 冒烟测试
docs/DEVELOPMENT.md # 开发文档(架构、里程碑、开发日志)
里程碑
- [x] v1.0:MCP 服务器 +
run_command工具(冒烟测试全绿) - [ ] v1.1:
run_agent_task多 Agent 接入(headless 桥接) - [ ] v1.2:安全壳(危险命令拦截 + 密钥脱敏 + 审计日志)
- [ ] v1.3:Web 仪表盘(加分项)
License
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.