HippoRAG long-term memory

The hipporag MCP server keeps a persistent knowledge-graph index on disk. Indexed passages survive across sessions and projects, so check it before saying you don't know something the user may have indexed earlier.

Choosing a tool

• retrieve: the default for answering questions. It returns ranked passages with source_id and metadata and makes no LLM call. Read the passages, answer in your own words, and cite source_ids. Use top_k 5, 10 for most questions and up to ~20 for broad or multi-hop ones.
• rag_qa: only when the user explicitly wants HippoRAG's own answer, for example when comparing against the paper's QA pipeline. It costs an extra server-side LLM call, and you still need to check its answer against the returned passages.
• index_stats: check that the index is non-empty and see which LLM and embedding model it uses. Call it first when a retrieval fails or comes back empty.
• index: add documents (see below).
• delete: remove passages by source_id (preferred) or by exact passage text as returned by retrieve. Deletion cannot be undone, so confirm with the user before deleting anything they did not name explicitly.

Indexing