Search the web using various search engines
AI agents call search.web to retrieve information from MCP Fullstack without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Web search is a fundamental read operation that queries external data sources and returns results. It has no side effects on the system or external services—it only retrieves information. The blast radius of misuse is minimal (e.g., excessive queries, information gathering), posing no risk to data integrity, system execution, or financial operations.
From the tool's definition Tool name 'search.web' combined with description 'Search the web using various search engines' indicates data retrieval without modification or execution. No mention of command execution, data modification, deletion, or financial operations.
Attacks that exploit this kind of access
Search the web using various search engines. It is categorised as a Read tool in the MCP Fullstack MCP Server, which means it retrieves data without modifying state.
Register the MCP Fullstack MCP server in PolicyLayer and add a rule for search.web: 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 MCP Fullstack. Nothing to install.
search.web 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 search.web 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 search.web. 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.
search.web is provided by the MCP Fullstack MCP server (jacobfv/mcp-fullstack). 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 →