MCP 服务器

Insights Knowledge Base MCP Server

A free, plug-and-play knowledge base server that provides access to 10,000+ insight reports with secure local data storage.

Tools

search_report_profile

该方法用于查询多条件组合的报告概况。LLM需根据用户输入的消息(user_message)提炼出以下参数。 ️⚠️注意：当LLM引用该方法返回的结果时，必须用markdown格式明确、醒目告知用户引自哪篇报告和具体访问地址！比如“**观点引自《Open source technology in the age of AI》** ```Path <如果"file_uri"不为空，这里完整填入file_uri> ```” 参数： keywords: List[str] = None, 整篇报告的关键词。 ⚠️注意： - 将每个关键词自动翻译为中英双语 - 例如用户输入"帮我查询下科技上市公司前景哈？" → 应转换为["科技", "technology", "上市公司", "publicly listed company"， "前景", "prospect"] title: str = "", 报告标题包含词。 content: str = "", 报告内容包含词。 publisher: str = "", 报告发布者。 start_date: Optional[datetime] = None, 报告查询开始日期。 end_date: Optional[datetime] = None, 报告查询结束日期。 match_logic: str = "OR", 匹配逻辑。"OR" 或者 "AND"，二选一，**优先用 "OR"**。返回： results：报告概览 - "file_name": 报告名称 - "topic": 报告主题 - "content": 报告整体摘要 - "published_by": 发布机构 - "published_date": 发布日期 - "file_full_path": 报告存放于本地地址 - "matched_keywords": 匹配关键词组 current_page：当前页码。⚠️当前页码小于总页码时，LLM需在结尾处提示用户可输入“下一页”查询更多记录。 total_pages：总页数 total_matches：总匹配记录条数

search_content_detail

该方法用于查询符合多条件组合的报告详情页面。LLM需根据用户输入的消息(user_message)提炼出以下参数。 ⚠️注意：当LLM引用该方法返回的结果时，必须用markdown格式明确、醒目告知用户引自哪篇报告和具体访问地址！比如“**观点引自《21世纪CEO的成功法则》第10、16页** ```Path <如果"file_uri"不为空，这里完整填入file_uri> ```” 参数： keywords: List[str] = None, 报告详情页的关键词。 ⚠️注意： - 将每个关键词自动翻译为中英双语 - 例如用户输入"帮我查询下科技上市公司前景哈？" → 应转换为["科技", "technology", "上市公司", "publicly listed company"， "前景", "prospect"] title: str = "", 报告详情页标题包含词。 content: str = "", 报告详情页内容包含词。 publisher: str = "", 报告发布者。 start_date: Optional[datetime] = None, 报告查询开始日期。 end_date: Optional[datetime] = None, 报告查询结束日期。 match_logic: str = "OR", 匹配逻辑。"OR" 或者 "AND"，二选一，**优先用 "OR"**。 page_index: int = 1, 页码，默认仅显示第一页。返回： results：报告详情 - file_name: 详情页来自于��份报告名 - page_number: 页码 - page_abstract: 摘要 - page_content: 完整内容 - page_keywords: 详情页关键词 - published_by: 报告发布机构 - published_date:报告发布日期 - file_full_path: 报告存放于本地地址 - matched_keywords: 匹配关键词组 current_page：当前页码。⚠️当前页码小于总页码时，LLM需在结尾处提示用户可输入“下一页”查询更多记录。 total_pages：总页数 total_matches：总匹配记录条数

README

Insights Knowledge Base(IKB) MCP Server

>>>中文版

🍭A free, plug-and-play knowledge base. Built-in with 10,000+ high-quality insight reports, packaged as MCP Server, and secure local data storage.

⚠️⚠️ All collected reports in this project come from free resources on official research report websites. ⚠️⚠️

Features

🍾 No configuration needed, truly plug-and-play. For private document parsing, configure VLM models and parameters in .env (e.g., VLM_MODEL_NAME=qwen2.5-vl-72b-instruct).
🦉 Permanently free - no need to waste effort collecting report resources. Welcome to share reliable, copyright-free report sources via issues.
📢 Committed to weekly report updates, but bug fixes depend on my mood (I'm not a programmer 🤭).

[ introduction video ][https://youtu.be/Mb8KbPo7EVM]

Installation (Beginner-Friendly)

💡Pro tip: Stuck? Drag this page to an LLM client (like DeepSeek) for step-by-step guidance. Actually, these instructions were written by DeepSeek too...

Prerequisites: Python 3.12+ (Download from official website and ADD ENVIRONMENT PATH)

Install UV:

pip install uv

1. Clone the project

git clone https://github.com/v587d/InsightsLibrary.git
cd InsightsLibrary

2. Create virtual environment

uv venv .venv  # Create dedicated virtual environment

# Activate environment
# Windows:
.\.venv\Scripts\activate
# Mac/Linux:
source .venv/bin/activate

3. Install core dependencies

uv pip install -e .  # Note the trailing dot indicating current directory

4. Create environment variables (for future needs)

notepad .env  # Windows
# Or
nano .env     # Mac/Linux

5. Configure MCP Server

VSCODE

Note: Replace <Your Project Root Directory!!!> with actual root directory.

{
  "mcpServers": {
    "ikb-mcp-server": {
      "command": "uv",
      "args": [
        "--directory",
        "<Your Project Root Directory!!!>", 
        "run",
        "ikb_mcp_server.py"
      ]
    }
  }
}

Cherry Studio
- Command: uv
- Arguments:

--directory
<Your Project Root Directory!!!>
run
ikb_mcp_server.py

Parse Private Documents

Version 0.1.0 has basic functionality - we'll improve this later. 😎

Upload PDF documents to the library_files folder
Manually run Python scripts:

# cd to project root
# Activate virtual environment
uv run decoder.py
# Wait for completion
uv run large_models.py
# Wait for completion
# Data is now updated in the database