
DocDeploy
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.
- tools
- 5
- transport
- HTTP
- last updated
- Apr 12, 2026
Tools
5 toolsPublic tool metadata for what this MCP can expose to an agent.
get_manifestFull document index — start here
Full document index — start here
No parameter schema in public metadata yet.
search_documentsFull-text search across all docs and sections
Full-text search across all docs and sections
No parameter schema in public metadata yet.
get_documentLoad a full document with section markers
Load a full document with section markers
No parameter schema in public metadata yet.
get_sectionLoad a specific section by marker
Load a specific section by marker
No parameter schema in public metadata yet.
list_documentsList all available documents
List all available documents
No parameter schema in public metadata yet.
Sponsors
Readme
DocDeploy
Enterprise document intelligence platform. Upload docs, PDFs, manuals, and notes — DocDeploy converts them to indexed Markdown and serves them via per-tenant MCP servers so AI agents can query your knowledge base.
How It Works
Upload → Convert to Markdown → Inject Section Markers → Index → Serve via MCP
- Upload any document (PDF, DOCX, PPTX, XLSX, HTML, TXT, CSV, JSON, XML)
- Convert to clean, structured Markdown with images preserved
- Index sections with navigational markers and full-text search
- Connect AI agents via MCP — they can search, browse, and read your docs
Architecture
┌─────────────────────────────────────────┐
│ apps/app Next.js dashboard │ ← Vercel
│ apps/web Marketing site │ ← Vercel
├─────────────────────────────────────────┤
│ packages/lib Converter pipeline│
│ packages/db Drizzle + Neon │
│ packages/workers Background jobs │ ← Render
│ packages/mcp-server MCP per tenant │ ← Render
└─────────────────────────────────────────┘
Tech Stack
Details
- Repository
- github.com/mrdulasolutions/docdeploy
- Website
- docdeploy.io
- Categories
- AI & LLM Tools, Documents & Knowledge
- Transport
- HTTP
- Registry
- MCP registry, active