feat(mcp): hy3-research-assistant — Deep Research MCP Server - #209
Open
cooldeveloper-code wants to merge 1 commit into
Open
feat(mcp): hy3-research-assistant — Deep Research MCP Server#209cooldeveloper-code wants to merge 1 commit into
cooldeveloper-code wants to merge 1 commit into
Conversation
- Deep research assistant with 9 MCP tools - Document classification and personalized recommendations - One-click install, Cursor/CodeBuddy configs, demo GIF
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
hy3-research-assistant-mcp 是一个基于 MCP(Model Context Protocol)协议的开源 Server,将腾讯 Hy3 的推理能力封装为即插即用的研究助手,接入 Cursor / CodeBuddy / WorkBuddy / Cline 等任意 MCP 客户端即可使用,无需额外开发。
应用场景:深度研究助手 — 网页搜索 + 文档阅读 + Hy3 深度分析 + 报告生成 + 个性化推荐
亮点 说明
🔌 即插即用 :stdio 模式,一条命令启动,兼容主流 MCP 客户端
🧠 Hy3 驱动 : 核心推理调用 Hy3 API(OpenAI 兼容),支持
reasoning_effort深度控制📚 智能分类 : 每次阅读文档自动 Hy3 分类,持久化用户兴趣历史
🔍 个性化推荐 : 基于历史阅读数据,自动搜索最新网页并生成推荐
📦 一键安装 :
install.ps1/install.sh,附完整 README 与中英文文档🎬 Demo 可复现 : 含 CLI Demo 脚本 + 10 帧动画 GIF,验证流程清晰
hy3-research-assistant-mcp/
├── pyproject.toml
├── README.md
├── .env.example
├── Makefile
├── src/
│ └── hy3_research_assistant_mcp/
│ ├── init.py
│ ├── server.py # MCP Server 主入口
│ ├── hy3_client.py # Hy3 API 封装
│ ├── search_client.py # 搜索客户端
│ ├── document_reader.py # 本地文件读取
│ ├── history_store.py # history_store.json 管理
│ └── tools/
│ ├── init.py
│ ├── search_web.py
│ ├── read_document.py
│ ├── read_and_classify.py
│ ├── get_recommendations.py
│ ├── deep_analyze.py
│ ├── synthesize_report.py
│ └── research_pipeline.py
├── prompts/
│ ├── classify.txt
│ ├── analyze.txt
│ ├── synthesize.txt
│ └── recommend.txt
└── examples/
├── codebuddy/
│ └── mcp_settings.json
├── cursor/
│ └── mcp.json
└── cline/
└── cline_mcp_settings.json
search_webread_documentread_and_classify_documentget_reading_historyget_personalized_recommendationsdeep_analyzesynthesize_reportresearch_pipelineget_interest_summary1️⃣ 文档阅读自动分类(需求扩展)
用户每次调用
read_and_classify_document时:~/.hy3-research/reading_history.jsonHY3_HISTORY_DIR自定义存储路径2️⃣ 基于历史的个性化推荐(需求扩展)
用户调用
get_personalized_recommendations时: