The Insights Knowledge Base MCP Server is a plug-and-play knowledge base server with built-in reports and local data storage capabilities.
- Search Functionality: Query reports using various criteria including keywords, title, content, publisher, and date range. Use
search_report_profile
for summaries andsearch_content_detail
for detailed page content. - Advanced Search Options: Combine search criteria using either OR or AND logic for more precise results.
- Automatic Translation: Keywords are automatically translated into both Chinese and English for broader searchability.
- Result Management: Handle large result sets with pagination support.
- Private Document Integration: Upload and parse private PDF documents into the database for future queries.
- Attribution Support: Ensure proper attribution with markdown formatting when referencing reports.
- Low Maintenance: Weekly updates to report database with bug fixes as needed.
Enables configuration of VLM models and parameters for private document parsing through environment variables
Used for cloning and managing the knowledge base repository which contains the insight reports
Provides access to report repository and allows users to contribute report sources through issues
Serves as the runtime environment for the knowledge base with specific version requirements (3.12+)
Insights Knowledge Base(IKB) MCP Server
🍭A free, plug-and-play knowledge base. Built-in with 10,000+ high-quality insights 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
- 🍾 Zero configuration required, designed for plug-and-play usage.
- 🚀 Built-in
Qwen3-Embedding-0.6B
embedding model, related reports can be retrieved through vector search.📢 Report details can also be searched via keyword retrieval. - 🍥 over 100 insights reports from well-known consulting firms such as McKinsey, PwC, and BAIN have been collected, including 6,000+ report pages, covering 70+ topics.
- 💎 Real-time online browsing of full reports in MCP Client.
- 🎉 Ultra-fast response: All Function_call returns typically <1 second, keyword-based queries <150ms.
- 🎨 Paste private local documents into the library_files folder (create it manually if absent; name must match). Configure VLM models/parameters in .env (e.g., VLM_MODEL_NAME=qwen2.5-vl-72b-instruct) for local document extraction, parsing, and recognition.
- 🦉 Permanently free—no wasted effort collecting reports. Share reliable, copyright-compliant resources via issues.
- 🔔 Commit to weekly report updates; bug fixes depend on personal whim (I'm not an engineer 🤭).
Optimizations as of June 30
- Added 2000+ report pages.
Future Directions
- Continuous report updates.
- Prompt engineering optimization.
Newest Files Profile
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:
1. Clone the project(Confirm successfully installed Git and Git LFS)
2. Create virtual environment
3. Install core dependencies
4. Create environment variables (for future needs)
5. Configure MCP Server
- VSCode.Cline
Note: Replace
<Your Project Root Directory!!!>
with actual root directory.
- Cherry Studio
- Command:
uv
- Arguments:
- Command:
Adding Private Documents to ikb_mcp_server
- Configure VLM models and parameters in
.env
: - Upload the PDF document to the
library_files
folder under the project root directory. - Manually run main.py.
License
This project is licensed under the MIT License. See the LICENSE file for details.
Optimization Updates as of June 17th
- 💡Optimized
models.py
: Improved data query efficiency by 1,000% - 💡Optimized
extractor.py
: Slightly enhanced PDF extraction efficiency - 💡Optimized
recognizer.py
: Boosted image comprehension efficiency by 50% - 💡Optimized
ikb_mcp_server.py
:- Added pagination functionality
- Displayed local paths of referenced files
- 💡Add MIT License(https://github.com/v587d/InsightsLibrary/pull/1#issuecomment-2969226661)
- 📦 Overall compressed project package size reduced by approximately 50%
- 💡Streamline Private Document Handling
- 💡Fixed other identified bugs
Optimizations as of June 22
- Added
embedder.py
: Implements text vectorization indexing via local Qwen3-Embedding-0.6B model, stored in faiss_index. - Modified
main.py
: Closed-loop workflow PDFExtractor → IMGRecognizer → Embedder (optional). - New
@mcp.tool(): get_similar_content_by_rag
: Finds most similar document content via vector similarity (RAG). - All admin-uploaded reports now support online viewing → Removed library_files folder to reduce project size.
- Added 2000+ report pages.
local-only server
The server can only run on the client's local machine because it depends on local resources.
A free, plug-and-play knowledge base server that provides access to 10,000+ insight reports with secure local data storage.
Related MCP Servers
- -securityAlicense-qualityThis project is based on the Knowledge Graph Memory Server from the MCP servers repository and retains its core functionality.Last updated -44107TypeScriptMIT License
- AsecurityAlicenseAqualityA server that enables LLMs to programmatically interact with Logseq knowledge graphs, allowing creation and management of pages and blocks.Last updated -1017PythonMIT License
- -securityAlicense-qualityA powerful knowledge management system that forges wisdom from experiences, insights, and best practices. Built with Qdrant vector database for efficient knowledge storage and retrieval.Last updated -3TypeScriptMIT License
- -securityFlicense-qualityIntelligent knowledge base management tool that enables searching, browsing, and analyzing documents across multiple datasets with smart document analysis capabilities.Last updated -10Python