deepseek-pp — MCP Server by zhu1090093659

by zhu1090093659 · MCP Server · ★ 833

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

About deepseek-pp

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 — 执行结果渲染成类似「已思考」的折叠区块,例如「已执行工具(2次)」并逐条展示结果 多工具连续执行 — 同一条回复可以执行多次工具调用,适合把多个独立事实分别保存为多条记忆 刷新后恢复 — 工具执行记录在刷新会话后仍能恢复展示 速度显示 — 回复生成时在输入框旁显示实时 ,便于判断当前会话是否仍在高速输出 Agent 式持续执行 持续推进任务 — 像 Claude Code / Codex 一样,模型可以根据工具结果继续决定下一步,而不是只执行一次工具后停住 分步续跑 — MCP 工具结果会回传到同一会话继续生成,直到任务完成或不再需要调用工具 节奏控制 — 多步续跑会在连续请求之间自动留出间隔,减少长任务被平台校验打断的情况 Step 折叠区 — 连续执行过程按 Step 展示,已完成步骤自动折叠,长任务不会淹没正文 刷新后恢复 — 页面刷新后仍能恢复最近的工具执行过程和最终状态 可手动停止 — 长任务执行中可以直接停止后续续跑 悬浮宠物 状态联动 — DeepSeek 页面可显示「DeepSeek 小鲸鱼」,会跟随思考、输出、工具执行、成功和失败状态切换反馈 台词气泡 — 小鲸鱼会按当前状态显示简短台词,长时间思考、输出或工具执行时自动轮播 位置可调 — 支持固定在左下或右下,也可以直接拖动到自定义位置 外观可调 — 设置页可调整尺寸、透明度和动态漂浮效果 本地保存 — 开关、位置和外观配置保存在浏览器本地,刷新后继续生效 <img src="public/pet/deepseek-whale-pet-states.png" width="420" alt=

agentic-aiai-agentai-memoryautomationbrowser-extensionchrome-extensionconversation-exportdeepseekdeepseek-aiedge-extension

Quick Facts

Stars833
Forks113
LanguageTypeScript
CategoryMCP Server
Quality Score41.756/100
Open Issues5
Last Updated2026-06-19
Created2026-04-27
Platformsbrowser, cli, mcp, node
Est. Tokens~16k

Compatible Skills

These tools work well together with deepseek-pp for enhanced workflows:

  • claude-chromium-native-messaging — semantic(0.43)+complementary+rare_topics+similar_pop+shared_platform (59%)
  • Interceptor — semantic(0.42)+complementary+rare_topics+similar_pop+shared_platform (59%)
  • ctxport — semantic(0.27)+complementary+rare_topics+same_lang+similar_pop+shared_platform (59%)

deepseek-pp alternative? Top 6 similar tools

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 by SixHq · ⭐ 592

    Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server

  • tabularis by debba · ⭐ 1.2k

    A lightweight, cross-platform database client for developers. Supports MySQL, PostgreSQL and SQLite. Hackable

  • tuui by AI-QL · ⭐ 1.1k

    A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Mode

  • awesome-openclaw by SamurAIGPT · ⭐ 957

    A curated list of OpenClaw resources, tools, skills, tutorials & articles. OpenClaw (formerly Moltbot / Clawdb

  • context-space by context-space · ⭐ 804

    Ultimate Context Engineering Infrastructure, starting from MCPs and Integrations

  • pdf-reader-mcp by SylphxAI · ⭐ 787

    📄 Production-ready MCP server for PDF processing - 5-10x faster with parallel processing and 94%+ test covera

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is deepseek-pp?

deepseek-pp is DeepSeek Web browser extension: AI agent workspace with MCP tools, memory, Skills, automation, web search, and conversation export.. It is categorized as a MCP Server with 833 GitHub stars.

What programming language is deepseek-pp written in?

deepseek-pp is primarily written in TypeScript. It covers topics such as agentic-ai, ai-agent, ai-memory.

How do I install or use deepseek-pp?

You can find installation instructions and usage details in the deepseek-pp GitHub repository at github.com/zhu1090093659/deepseek-pp. The project has 833 stars and 113 forks, indicating an active community.

What are the best alternatives to deepseek-pp?

The top alternatives to deepseek-pp on Agent Skills Hub include Overture, tabularis, tuui. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

View on GitHub → Browse MCP Server tools