AI agents call lookup-resources to retrieve information from Spicedb without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries SpiceDB to retrieve resources matching specific permission criteria. It does not create, modify, delete, or execute operations with external effects. It is a read-only data retrieval operation, making it the least severe category. Low severity because misuse would at worst leak information about the permission model's structure, but cannot change state or trigger external actions.
From the tool's definition Tool description states it 'Finds all resources' — a query operation that retrieves data without modifying or deleting anything. The verb 'Finds' and the context of 'answering questions' confirm this is a retrieval/lookup function with no side effects.
Attacks that exploit this kind of access
Finds all resources of a specified type where a subject has a particular permission. This is useful for answering questions like. It is categorised as a Read tool in the Spicedb MCP Server, which means it retrieves data without modifying state.
Register the Spicedb MCP server in PolicyLayer and add a rule for lookup-resources: 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 Spicedb. Nothing to install.
lookup-resources 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 lookup-resources 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 lookup-resources. 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.
lookup-resources is provided by the Spicedb MCP server (samkim/spicedb-mcp-server). 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 →