Search the web using Bing Web Grounding to find the most current information.
AI agents call web_search to retrieve information from Azure AI Agent Service + Azure AI Search MCP Server 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 without modifying, executing code, deleting data, or committing financial resources. The operation is read-only and returns search results. Severity is low because the tool's primary risk is information leakage or manipulation through search results, which has minimal blast radius when used by an AI agent.
From the tool's definition Tool name is 'web_search' and description states it 'Search[es] the web using Bing Web Grounding to find the most current information.' This is a query operation with no side effects.
Attacks that exploit this kind of access
Search the web using Bing Web Grounding to find the most current information. It is categorised as a Read tool in the Azure AI Agent Service + Azure AI Search MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Azure AI Agent Service + Azure AI 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 Azure AI Agent Service + Azure AI 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 Azure AI Agent Service + Azure AI Search MCP Server MCP server (0lovesakura0/mcp-server-azure-ai-agents-main). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
web_search is one line of Azure AI Agent Service + Azure AI Search MCP Server's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →