Search knowledge graph
AI agents call graphiti_search to retrieve information from Garza Home MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries data from a knowledge graph without creating, modifying, deleting, or executing external operations. Even in a home automation context, searching a knowledge graph poses minimal risk—it only accesses information. The severity is low because misuse would be limited to unauthorized information disclosure with no destructive or operational impact.
From the tool's definition Tool name 'graphiti_search' and description 'Search knowledge graph' indicate a query/retrieval operation with no side effects. The verb 'search' is a canonical Read operation.
Attacks that exploit this kind of access
Search knowledge graph. It is categorised as a Read tool in the Garza Home MCP MCP Server, which means it retrieves data without modifying state.
Register the Garza Home MCP server in PolicyLayer and add a rule for graphiti_search: 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 Garza Home MCP. Nothing to install.
graphiti_search 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 graphiti_search 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 graphiti_search. 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.
graphiti_search is provided by the Garza Home MCP server (itsablabla/garza-home-mcp). 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 →