AI agents call get_performance to retrieve information from Flour Ads without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name and the server's stated capability to check performance indicate this retrieves or queries performance data from ad campaigns without side effects. No modifying, destructive, or financial operations are evident from the naming. Confidence is slightly reduced due to empty description, but the naming convention and server context strongly suggest a read operation.
From the tool's definition Tool name 'get_performance' indicates retrieval of performance metrics without modification. Server description mentions 'checking performance' as a read-only operation alongside deployments and budget management.
Attacks that exploit this kind of access
get_performance. It is categorised as a Read tool in the Flour Ads MCP Server, which means it retrieves data without modifying state.
Register the Flour Ads MCP server in PolicyLayer and add a rule for get_performance: 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 Flour Ads. Nothing to install.
get_performance 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 get_performance 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 get_performance. 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.
get_performance is provided by the Flour Ads MCP server (wayy-research/flour-ads). 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 →