Loading connector details…
Loading connector details…
Choose a unique username to continue using AgentHotspot
by jgravelle • Uncategorized
An MCP server for AI-native, token-efficient navigation of documentation by section.
Token-efficient, precise access to specific documentation sections.
Explore large documentation sets without reading entire files.
Stable, structured navigation of documentation preserving hierarchy.
jDocMunch MCP indexes documentation sets by heading hierarchy and section structure, enabling AI agents to retrieve precise sections with byte-precise extraction from original files. This approach reduces token usage, improves context relevance, and enhances agent reliability by preserving the authored document structure. It supports multiple documentation formats and integrates with MCP-compatible clients like Claude Desktop and Google Antigravity.
Index a local folder containing documentation files (.md, .txt, .rst). Parses by heading hierarchy into sections for efficient retrieval. Set use_embeddings=true to enable semantic search.
Index a GitHub repository's documentation. Fetches .md/.txt files, parses sections, and saves to local storage. Set use_embeddings=true to enable semantic search.
List all indexed documentation repositories.
Get a flat table of contents for all sections in a repo, sorted by document order. Content is excluded — use get_section to retrieve content.
Get a nested table of contents tree per document. Shows parent/child heading relationships. Content is excluded.
Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.