About Neurag
Neurag is an MCP server in the RAG category: hierarchical knowledge base for AI. An MCP server that indexes your documents into a trigger-navigable node/chunk graph with hybrid retrieval — a permanent vault, no decay. Runs standalone or behind the Gray Matter gateway.
Install
From source
git clone https://github.com/recla93/NeuragThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (6)
knowledge_add_chunks(node_name, chunks)Attach previously indexed chunks to a node
Parameters not published.
knowledge_add_node(name, node_type, parent_name?, triggers?)Create a node in the hierarchy
Parameters not published.
knowledge_confirm(...)Mark results as useful together, so their links strengthen
Parameters not published.
knowledge_import(mapping)Bulk-import a folder tree from a YAML mapping, deterministically
Parameters not published.
knowledge_index(path)Chunk a file or directory → returns JSON list of chunks (manual path)
Parameters not published.
knowledge_query(query, top_n?)Search: vector **and** BM25 always, fused with RRF, then MMR-diversified
Parameters not published.
Ask AI
✦
Ask AI about Neurag
Powered by Claude · Grounded in docs
I know everything about Neurag. Ask me about installation, configuration, usage, or troubleshooting.
Security checks
6 checks have not been run yet.