Multi-Document RAG
MCP-RAG is a server implementation that enables large file processing and retrieval-augmented generation capabilities for AI assistants. Developed by Anurag Bombarde, it provides tools for extracting content from various document formats (PDF, DOCX, PPTX, Excel, CSV, and images) with OCR support, creating vector embeddings using OpenAI or SentenceTransformer models, and performing semantic searches across document collections. The implementation features robust handling of large files through chunking strategies, multi-vector store support with ChromaDB and Milvus integration, and comprehensive document processing with enhanced OCR capabilities for scanned documents and images.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- media
- Source
- PulseMCP
- Repository
- github.com/anuragb7/mcp-rag
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Multi-Document RAG from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.