Doc Lib MCP

stdio

An MCP server for document ingestion, chunking, semantic search, and note management.

Install

npx @modelcontextprotocol/inspector

add-note Add a new note to the in-memory note store
ingest-string Ingest and chunk a markdown or plain text string provided via message
ingest-markdown Ingest and chunk a markdown (.md) file
ingest-python Ingest and chunk a Python (.py) file
ingest-openapi Ingest and chunk an OpenAPI JSON file
ingest-html Ingest and chunk an HTML file
ingest-html-url Ingest and chunk HTML content from a URL (optionally using Playwright for dynamic content)
smart_ingestion Extracts all technically relevant content from a file using Gemini, then chunks it using robust markdown logic
search-chunks Semantic search over ingested content
delete-source Delete all chunks from a given source
delete-chunk-by-id Delete one or more chunks by id
update-chunk-type Update the type attribute for a chunk by id
ingest-batch Ingest and chunk multiple documentation files (markdown, OpenAPI JSON, Python) in batch
list-sources List all unique sources (file paths) that have been ingested and stored in memory, with optional filtering by tag or semantic search
get-context Retrieve relevant content chunks (content only) for use as AI context, with filtering by tag, type, and semantic similarity
update-chunk-metadata Update the metadata field for a chunk by id
tag-chunks-by-source Adds specified tags to the metadata of all chunks associated with a given source (URL or file path). Merges with existing tags
list-notes List all currently stored notes and their content