AI agents call veroq_web_search 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.
This tool retrieves and displays information from web sources. It performs no write operations, does not execute code or commands, does not delete data, and does not commit financial transactions. The trust scoring feature is a metadata annotation that does not alter the underlying data or trigger external actions. This is a classic Read category operation: retrieving data without side effects.
From the tool's definition Tool description states "Search the live web" which is a query/retrieval operation with no modification, deletion, or execution of external code. The optional "trust scoring" is an analytical overlay on retrieved results, not an action with side effects.
Attacks that exploit this kind of access
Search the live web with optional VEROQ trust scoring on results. WHEN TO USE: When intelligence briefs don. 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_web_search: 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_web_search 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_web_search 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_web_search. 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_web_search 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 →