Search for nodes in the graph memory.
AI agents call search_memory_nodes to retrieve information from local-RAG-backend without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches and retrieves data from the graph memory structure without creating, modifying, deleting, or executing any operations. It is a pure read operation analogous to query or search functions. The blast radius is minimal as misuse would only surface existing data.
From the tool's definition Tool name 'search_memory_nodes' and description 'Search for nodes in the graph memory' indicate a query/retrieval operation with no modification or execution of external commands.
Attacks that exploit this kind of access
Search for nodes in the graph memory. It is categorised as a Read tool in the local-RAG-backend MCP Server, which means it retrieves data without modifying state.
Register the local-RAG-backend MCP server in PolicyLayer and add a rule for search_memory_nodes: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches local-RAG-backend. Nothing to install.
search_memory_nodes is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search_memory_nodes rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for search_memory_nodes. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
search_memory_nodes is provided by the local-RAG-backend MCP server (suwa-sh/local-rag-backend). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →