Fetch only content under a specific heading. Case-insensitive heading match.
AI agents call web_fetch_section to retrieve information from Smart Webfetch without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves a section of web content by heading match. It performs a query operation (locate and return data) with no side effects, no code execution, no data modification, and no resource destruction. It is purely read-only information retrieval, the least severe category.
From the tool's definition Tool name is 'web_fetch_section' and description states 'Fetch only content under a specific heading' — fetches/retrieves data without modification or side effects.
Attacks that exploit this kind of access
Fetch only content under a specific heading. Case-insensitive heading match. It is categorised as a Read tool in the Smart Webfetch MCP Server, which means it retrieves data without modifying state.
Register the Smart Webfetch MCP server in PolicyLayer and add a rule for web_fetch_section: 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 Smart Webfetch. Nothing to install.
web_fetch_section 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_fetch_section 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_fetch_section. 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_fetch_section is provided by the Smart Webfetch MCP server (mathisto/smart-webfetch-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 →