Generate creative names. Free.
AI agents call name_generator to retrieve information from Agent Treats without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool generates content (creative names) on demand without modifying persistent data, executing code, or affecting external systems. It is a read-like operation that returns generated content without side effects, consistent with a fun/entertainment tool in the Agent Treats sample collection. Severity is low because even if misused, name generation poses minimal harm.
From the tool's definition Tool description states 'Generate creative names. Free.' with no mention of side effects, data modification, execution, deletion, or financial operations. The tool retrieves or generates data without persisting changes or triggering external actions.
Attacks that exploit this kind of access
Generate creative names. Free. It is categorised as a Read tool in the Agent Treats MCP Server, which means it retrieves data without modifying state.
Register the Agent Treats MCP server in PolicyLayer and add a rule for name_generator: 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 Agent Treats. Nothing to install.
name_generator 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 name_generator 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 name_generator. 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.
name_generator is provided by the Agent Treats MCP server (montecbmd/agent-treats-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 →