hKG Ontologizer
This MCP server transforms text content and web URLs into structured knowledge graphs using AI-powered entity extraction and relationship mapping, built with Python and Gradio for the MCP Hackathon 2025. The implementation supports multiple AI model providers (Ollama, LM Studio, hosted APIs) for flexible deployment, processes large content through intelligent chunking with real-time visualization updates, and integrates with Neo4j for graph storage and Qdrant for vector embeddings using UUIDv8 for unified entity tracking. Features include real-time SVG graph generation with NetworkX and matplotlib, comprehensive file format support (PDF, DOCX, CSV, HTML), and enhanced metadata tracking for knowledge graph lineage, serving researchers analyzing large documents, developers building knowledge management systems, and teams needing automated extraction of structured insights from unstructured content with persistent graph storage capabilities.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-02.
Scan details: Circle-IR · 2026-09-02 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- devops-ci
- Source
- PulseMCP
- Author type
- human
- Last scanned
- 2026-09-02
- Updated
- 2026-09-02
Use via MCP
Resolve hKG Ontologizer from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.