DocNav
DocNav is an MCP server that enables LLMs to intelligently read, navigate, and analyze long-form documents by breaking them into hierarchical tree structures similar to DOM nodes. The implementation supports Markdown and PDF files through pluggable processors, converting documents into navigable sections with auto-generated UUIDs for security, and provides tools for outline generation, section-by-section reading, content search, and contextual navigation with parent-child-sibling relationships. Built with a modular architecture using Python, it's particularly valuable for document analysis workflows where LLMs need to understand document structure and navigate large texts systematically rather than processing them as monolithic blocks.
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 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/shenyimings/docnav-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve DocNav 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.