Create a new custom agent. Two paths:\n\n
AI agents use wafle_agents_create to create or update resources in wafle MCP server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your wafle MCP server environment.
This tool creates a new agent entity within the wafle commerce platform, which is a reversible write operation. While creating agents could have downstream execution implications if those agents autonomously perform actions, the tool itself is fundamentally a Write operation—it modifies system state by adding a new agent.
From the tool's definition Tool name 'wafle_agents_create' and description indicating it 'Create a new custom agent' demonstrates data creation functionality.
Attacks that exploit this kind of access
Create a new custom agent. Two paths:\n\n. It is categorised as a Write tool in the wafle MCP server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the wafle MCP server MCP server in PolicyLayer and add a rule for wafle_agents_create: 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 wafle MCP server. Nothing to install.
wafle_agents_create 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 wafle_agents_create 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 wafle_agents_create. 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.
wafle_agents_create is provided by the wafle MCP server MCP server (the33warehouse-tech/wafle-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 →