AI agents call web_fetch_tool to retrieve information from Web without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and presents existing web content in a different format (markdown). It has no side effects, does not modify data, execute code, delete resources, or commit financial transactions. The blast radius of misuse is minimal; an attacker could only exfiltrate information already publicly accessible. Classify as Read with low severity.
From the tool's definition Tool description states it 'Fetch[es] full content from a URL and return[s] it as markdown' — a retrieval operation with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
Fetch full content from a URL and return it as markdown. It is categorised as a Read tool in the Web MCP Server, which means it retrieves data without modifying state.
Register the Web MCP server in PolicyLayer and add a rule for web_fetch_tool: 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 Web. Nothing to install.
web_fetch_tool 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_tool 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_tool. 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_tool is provided by the Web MCP server (ryandam/essentialmcp). 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 →