Search the web for information about the given query
AI agents call web_search to retrieve information from Tavily Search 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 current information from the internet through a search API. It has no side effects, does not modify or delete data, and does not execute code or commit financial obligations. It is a straightforward read operation that queries an external search service and returns results to the user.
From the tool's definition Tool name is 'web_search' and description states 'Search the web for information about the given query' — retrieves information with no modification or deletion of data.
Attacks that exploit this kind of access
Search the web for information about the given query. It is categorised as a Read tool in the Tavily Search MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Tavily Search MCP Server 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 Tavily Search MCP Server. 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 Tavily Search MCP Server MCP server (mwalker-tmd/mcp-session-code). 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 →