List custom agents defined for a store. Each agent has system_prompt + tools whitelist + guardrails + trigger. Filter by status (draft/active/paused/archived) or trigger_type.
AI agents call wafle_agents_list to retrieve information from wafle MCP server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries existing agent configurations (system_prompt, tools, guardrails, trigger metadata) filtered by status or trigger type. It performs no modifications, deletions, or external operations. The data returned is read-only metadata about internal agent definitions. Blast radius is minimal — the only risk is information disclosure of internal agent configurations, which is low severity.
From the tool's definition Tool name 'wafle_agents_list' and description 'List custom agents defined for a store' — the verb 'list' is a retrieval operation with no side effects.
Attacks that exploit this kind of access
List custom agents defined for a store. Each agent has system_prompt + tools whitelist + guardrails + trigger. Filter by status (draft/active/paused/archived) or trigger_type. It is categorised as a Read tool in the wafle MCP server MCP Server, which means it retrieves data without modifying state.
Register the wafle MCP server MCP server in PolicyLayer and add a rule for wafle_agents_list: 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_list 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 wafle_agents_list 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_list. 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_list 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 →