List available vertical agent packs — pre-built agent configurations for specific domains. WHEN TO USE: To discover which agent packs are available before calling veroq_run_agent. Each pack is a curated workflow for a specific use case. RETURNS: List of agent packs with slug, name, description, r...
AI agents call veroq_agent_packs to retrieve information from Veroq without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and enumerates available agent pack configurations. It performs a read-only lookup operation that returns metadata about pre-built workflows without creating, modifying, executing, or deleting any data. The blast radius of misuse is minimal—an agent could only discover available packs, not instantiate or execute them (that would require veroq_run_agent).
From the tool's definition Tool description states 'List available vertical agent packs' and 'RETURNS: List of agent packs with slug, name, description, required inputs, and credit cost.' This is a query/discovery operation with no side effects.
Attacks that exploit this kind of access
List available vertical agent packs — pre-built agent configurations for specific domains. WHEN TO USE: To discover which agent packs are available before calling veroq_run_agent. Each pack is a curated workflow for a specific use case. RETURNS: List of agent packs with slug, name, description, required inputs, and credit cost. COST: 1 credit. EXAMPLE: {}. It is categorised as a Read tool in the Veroq MCP Server, which means it retrieves data without modifying state.
Register the Veroq MCP server in PolicyLayer and add a rule for veroq_agent_packs: 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 Veroq. Nothing to install.
veroq_agent_packs 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 veroq_agent_packs 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 veroq_agent_packs. 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.
veroq_agent_packs is provided by the Veroq MCP server (veroq-ai/veroq-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 →