Web search via agentic tool. Provider must support search capability.
AI agents call web_search to retrieve information from AgentSpawnMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Web search is a read-only operation that queries external web resources and returns results. It does not modify, delete, or create data. The only concern is that the provider must support search capability, but the operation itself is retrieval-only. Severity is low as misuse could at most expose search queries or retrieve unintended content.
From the tool's definition 'Web search via agentic tool' — retrieves information from the web, no side effects implied
Attacks that exploit this kind of access
Web search via agentic tool. Provider must support search capability. It is categorised as a Read tool in the AgentSpawnMCP MCP Server, which means it retrieves data without modifying state.
Register the AgentSpawn MCP server in PolicyLayer and add a rule for 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 AgentSpawnMCP. Nothing to install.
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 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 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.
web_search is provided by the AgentSpawn MCP server (sandsaber/agentspawnmcp). 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 →