
Mcp Documentation Server
The MCP Documentation Server provides local-first document management and semantic search using an embedded Orama vector database, offering hybrid search capabilities (full-text and vector similarity), intelligent chunking with parent-child relationships, and optional AI-powered analysis via Google Gemini. The server includes a built-in web dashboard for document management, drag-and-drop file uploads (.txt, .md, .pdf), and context window retrieval, while eliminating the need for external databases or cloud services through embedded vector embeddings and an LRU cache for performance optimization. It solves the problem of managing and searching through local documents without external dependencies while providing rich contextual information to language models through semantic understanding of document content.
- GitHub stars
- 344
- tools
- 12
- transport
- STDIO
- last updated
- Aug 27, 2026
Tools
12 toolsPublic tool metadata for what this MCP can expose to an agent.
add_documentAdd a document (title, content, optional metadata)
Add a document (title, content, optional metadata)
No parameter schema in public metadata yet.
list_documentsList all documents with metadata and content preview
List all documents with metadata and content preview
No parameter schema in public metadata yet.
get_documentRetrieve the full content of a document by ID
Retrieve the full content of a document by ID
No parameter schema in public metadata yet.
delete_documentRemove a document, its chunks, database entries, and associated files
Remove a document, its chunks, database entries, and associated files
No parameter schema in public metadata yet.
process_uploadsProcess all files in the uploads folder (chunking + embeddings)
Process all files in the uploads folder (chunking + embeddings)
No parameter schema in public metadata yet.
get_uploads_pathReturns the absolute path to the uploads folder
Returns the absolute path to the uploads folder
No parameter schema in public metadata yet.
list_uploads_filesLists files in the uploads folder with size and format info
Lists files in the uploads folder with size and format info
No parameter schema in public metadata yet.
get_ui_urlReturns the Web UI URL (e.g. http://localhost:3080) — useful to open the dashboard or to locate the uploads folder from the browser
Returns the Web UI URL (e.g. http://localhost:3080) — useful to open the dashboard or to locate the uploads folder from the browser
No parameter schema in public metadata yet.
search_documentsSemantic vector search within a specific document
Semantic vector search within a specific document
No parameter schema in public metadata yet.
search_all_documentsHybrid (full-text + vector) cross-document search
Hybrid (full-text + vector) cross-document search
No parameter schema in public metadata yet.
get_context_windowReturns a window of chunks around a given chunk index
Returns a window of chunks around a given chunk index
No parameter schema in public metadata yet.
search_documents_with_aiAI-powered search using Gemini (requires GEMINI_API_KEY)
AI-powered search using Gemini (requires GEMINI_API_KEY)
No parameter schema in public metadata yet.
Sponsors
Readme
MCP Documentation Server
Local-first document management and semantic search for AI coding agents. No external databases, no cloud APIs, no vendor lock-in.
Details
- Repository
- github.com/andrea9293/mcp-documentation-server
- Categories
- Documents & Knowledge, Search & Web Crawling
- Package
@andrea9293/mcp-documentation-server- Transport
- STDIO
- Registry
- MCP registry, active

