MCP Server for zmp knowledge base
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"zmp-knowledge-store-mcp-server","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# ZMP Knowledge Store MCP Server      A high-performance MCP (Model Context Protocol) server for managing knowledge store content with multi-modal RAG capabilities, powered by Qdrant vector store with hybrid search, chat history logging, configurable collections, and advanced image analysis features. **Latest Version: 0.3.9.2** - Enhanced with PyTorch security fixes, manual RRF implementation, and optimized Docker builds. --- ## Recent Updates (v0.3.9.2) ### 🔒 Security & Compatibility Fixes - **PyTorch Security**: Upgraded to PyTorch 2.6.0+cpu to resolve CVE-2025-32434 vulnerability - **Torchvision Compatibility**: Fixed torchvision 0.21.0+cpu compatibility with CPU-only PyTorch - **NumPy/SciPy Stability**: Resolved compatibility issues with Python 3.12 and ML dependencies ### 🚀 Performance Improvements - **Manual RRF Implementation**: Replaced `ranx` dependency with custom Reciprocal Rank Fusion (RRF) implementation - **Docker Optimizations**: CPU-only PyTorch builds for faster deployment and smaller images - **Network Resilience**: Enhanced SSL handling and timeout configurations for reliable builds ### 🐛 Bug Fixes - **Startup Warnings**: Removed `get_collection_stats` warning for cleaner startup logs - **Dependency Management**: Improved Poetry + pip hybrid installation strategy - **Error Handling**: Enhanced error handling and logging throughout the application --- ## Python File Structure ``` zmp_knowledge_store/ ├── __init__.py # Package initialization & metadata ├── config.py # Configuration management with S3 integration ├── knowledge_store.py # Main knowledge store lo…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.