Skip to content

AI tools, MCP servers and agent skills for rag

41 MCP servers, 2 AI tools and 1 agent skill for rag in files and documents, including PageIndex, WeKnora and Nemo retriever, most popular first. 12 of the 44 are listed as free or open source. Each one is written up from its own site or README, with pricing, platforms and alternatives.

Showing 1–10 of 10

  1. Vectorless RAG engine that finds answers by reasoning over a document's page tree

    • Open source
    • Open-source agent
    • 40.5K GitHub stars
    • Files and documents
  2. Open-source knowledge framework for RAG Q&A, agent tasks and auto-built wikis

    • Open source
    • Open-source agent
    • 37.7K GitHub stars
    • Knowledge and memory
  3. Lets your agent ingest, index and query document collections with the NeMo Retriever CLI

    • Open source
    • 4K GitHub stars
    • Design and media
  4. haiku.rag

    MCP server

    Local-first RAG that answers from your documents with page and section citations

    Runs locally
    • Open source
    • Knowledge and memory
  5. Search a local folder of documents and check answers against them, with no API key

    Runs locally
    • 2 tools
    • Open source
    • Knowledge and memory
  6. md-chunk-lite

    MCP server

    Split Markdown into heading-aware chunks for RAG, with paths and line numbers

    Runs locally
    • Open source
    • AI models and LLM tooling
  7. Gives agents a PDF's heading tree and section text so they read only what they need

    Runs locally
    • 4 tools
    • Open source
    • Files and documents
  8. markitai

    MCP server

    Convert documents, images and web pages to Markdown from any MCP client

    Runs locally
    • 4 tools
    • Open source
    • Files and documents
  9. DocuSense

    MCP server

    Local MCP server that lets AI agents read PDFs and specs by section with cited quotes

    Runs locally
    • Open source
    • Files and documents
  10. lilbee

    MCP server

    Local AI search over your files, code and crawled sites, with cited answers and a built

    Runs locally
    • Open source
    • Files and documents