by zhu1090093659 · MCP Server · ★ 1.9k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
npx deepseek-pp-shell-host install --browser chrome --extension-id <扩展ID>
git clone https://github.com/zhu1090093659/deepseek-pp.gitTaken from the project's README on GitHub. Check the security audit before running it.
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 1,853 |
| Forks | 295 |
| Language | TypeScript |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 62/100 |
| Open Issues | 30 |
| Last Updated | 2026-08-13 |
| Created | 2026-04-27 |
| Platforms | browser, cli, mcp, node |
| Est. Tokens | ~16k |
DeepSeek++ 为 DeepSeek 网页版注入 类原生工具调用、MCP 工具系统、Agentic 记忆系统、Skill 技能系统、系统提示词预设、Agent 式持续执行 和 自动化任务 的 Chrome / Edge / Firefox 扩展。 让 DeepSeek 像支持原生 tools 一样自动执行记忆保存、更新、删除和 MCP 工具调用，拥有跨对话长期记忆，并通过 指令一键切换专家模式。Agent 式持续执行让模型像 Claude Code / Codex 一样，在工具调用、结果回传和下一步生成之间持续推进任务；自动化任务则负责把固定任务放进独立会话里立即触发或按计划触发。 核心功能 类原生工具调用 自动识别与执行 — 模型输出工具调用请求后，扩展自动识别并执行，不需要用户复制或手动确认 隐藏原始调用 — 页面不会暴露工具调用的技术细节，只展示简洁的执行结果 原生观感 —...
These tools work well together with deepseek-pp for enhanced workflows:
Looking for a deepseek-pp alternative? If you're comparing deepseek-pp with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server
🔮 Platform-neutral Browser Use for AI agents: real Chrome automation with a CLI + SDKs, no lock-in, dead simp
TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to c
Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budget
Open-source AI browser agent for Chrome and Firefox (monorepo) 🧠
A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Mode
Explore other popular mcp server tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: