This connects Claude to a multi-tenant document intelligence platform that converts PDFs, DOCX, PPTX, XLSX, and other formats into indexed Markdown with section markers. You get five tools: get_manifest for the full document index, search_documents for full-text queries, get_document to load complete files, get_section to fetch specific chunks, and list_documents for inventory. The pipeline preserves images via Cloudflare R2 and infers structure from PDFs using headings and numbering patterns. Each tenant gets an isolated MCP server over streamable HTTP. Reach for this when you need Claude to search and retrieve from an enterprise knowledge base without manually copying docs into context windows.
claude mcp add --transport http io.docdeploy.www-mcp-server https://mcp.docdeploy.io/mcp