AI agents call web_search to retrieve information from Maple without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
web_search retrieves publicly available information and returns results without creating, modifying, deleting, or executing any actions. It matches the Read category definition: 'retrieves or queries data; no side effects (search, list, get, fetch).' The severity is low because misuse would only surface existing public information, not cause harm through unintended modifications, deletions, or external operations.
From the tool's definition Tool description states it 'Search[es] the public web for a query and return[s] ranked snippets with URLs.' This is purely informational retrieval with no side effects.
Attacks that exploit this kind of access
Search the public web for a query and return ranked snippets with URLs. It is categorised as a Read tool in the Maple MCP Server, which means it retrieves data without modifying state.
Register the Maple 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 Maple. 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 Maple MCP server (omar2001ramadan/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 →