Search the graph memory for relevant facts.
AI agents call search_memory_facts 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 an existing graph database for facts—a read-only operation that retrieves information without modifying state. The use of 'search' and 'for' (indicating lookup) and absence of any destructive, write, or execute keywords confirms this is a Read category tool.
From the tool's definition Tool name 'search_memory_facts' and description 'Search the graph memory for relevant facts' indicate a query/retrieval operation with no mention of data creation, modification, deletion, or side effects.
Attacks that exploit this kind of access
Search the graph memory for relevant facts. 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_facts: 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_facts 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_facts 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_facts. 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_facts 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 →