RAG with PDF & MCP: agent access to docs

# PDF ingestion to Qdrant and semantic search via MCP for AI agents

This automation streamlines document ingestion and semantic retrieval for private knowledge bases. Built on n8n with LangChain, Ollama, and Qdrant, it enables secure, local RAG workflows for AI agents using MCP.

## Who it´s for
- Developers building RAG systems with private documents
- AI agent teams using MCP to access contextual knowledge
- Automation specialists working with local LLMs and vector databases

## What the automation does
- Receives PDF files via HTTP webhook from a form submission
- Splits text into chunks and generates embeddings using local Ollama instance
- Stores vector embeddings in a local Qdrant database
- Runs an MCP server to accept queries from clients
- Performs semantic search and returns relevant context snippets
- Integrates all steps via LangChain nodes in n8n

## What´s included
- Ready-to-use n8n workflow
- Trigger logic for form submissions and webhooks
- Integrations with Qdrant, Ollama, MCP (STDIO), and HTTP forms
- Basic setup and adaptation guide

## Requirements for setup
- Access to a running n8n instance (local or cloud)
- Active Qdrant database (local or network-accessible)
- Ollama server with a loaded embedding model
- MCP client (STDIO) to receive agent queries
- Webhook-capable form (e.g., HTML form or Airtable)

## Benefits and outcomes
- Automatic indexing of new documents without manual input
- Fast, context-aware retrieval for AI agents
- Full data control — runs locally or in a private network
- Scalable knowledge base that grows with new PDFs without reconfiguration

## Important: template only
Important: you are purchasing a ready-made automation workflow template only. Rollout into your infrastructure, connecting specific accounts and services, 1:1 setup help, custom adjustments for non-standard stacks and any consulting support are provided as a separate paid service at an individual rate. To discuss custom work or 1:1 help, contact via chat