Select best prompt candidate for given context
AI agents use gepa_select_optimal to create or update resources in Prompt Auto-Optimizer MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Prompt Auto-Optimizer MCP environment.
An AI agent can call gepa_select_optimal faster than any human can review — one bad instruction and it creates or modifies resources in Prompt Auto-Optimizer MCP by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Select best prompt candidate for given context. It is categorised as a Write tool in the Prompt Auto-Optimizer MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Prompt Auto-Optimizer MCP server in PolicyLayer and add a rule for gepa_select_optimal: 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 Prompt Auto-Optimizer MCP. Nothing to install.
gepa_select_optimal is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the gepa_select_optimal 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 gepa_select_optimal. 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.
gepa_select_optimal is provided by the Prompt Auto-Optimizer MCP server (sloth-wq/prompt-auto-optimizer-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.