$ loading_
Search locally indexed PDF docs with citations and context for LLM agents.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "rag-mcp" yet — see the docs or source repo.
Search the locally indexed PDF documents for "pros and cons of vector retrieval" and return relevant passages with citations.
Returns matching content, source citations, and context snippets for follow-up QA.
Retrieve "permission configuration" from local product manual PDFs and prepare the most relevant context for answering a user question.
Outputs the most relevant document excerpts and preserves citations for the agent.
Run both semantic and keyword search for "transformer interpretability" across locally indexed research paper PDFs and return cited passages.
Returns results combining semantic and keyword matches, along with citations and context.
Developers or researchers can index local PDF documents and let an LLM agent query them in read-only mode. This helps the agent answer with citations and supporting context.
When a team needs to find a topic across many PDF manuals, this tool can use hybrid semantic and keyword search. It is useful for locating relevant passages instead of manually paging through documents.
In document-grounded QA workflows, this tool can return citations and context snippets. It fits use cases where source traceability matters and unsupported answers should be reduced.
It provides read-only MCP search tools that run hybrid semantic and keyword search over locally indexed PDF documents, returning citations and context for LLM agents.
From the description, you at least need locally indexed PDF documents first. Other prerequisites are not provided here; see the source repository.
It supports hybrid semantic and keyword search rather than relying only on literal term matching, and it can return citations and context for document-grounded agent responses.
Ingest PDFs, run semantic search, and answer questions with source citations.
Index and semantically search code, PDFs, and documents with exact citations.
Search local documents with vector similarity for RAG answers.
Search PDFs with LLM reasoning to find relevant content and answers.
Index local documents and run hybrid semantic-keyword search on-device.
Retrieve technical documentation through MCP for accurate on-demand LLM references.