AI agents call fetch to retrieve information from Mcp Web without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs read-only retrieval of web content with no side effects. GET requests are idempotent and cannot modify server state. The restriction to GET requests and focus on content extraction further confirms this is a passive information retrieval operation. Low severity due to minimal blast radius—the worst outcome is accessing unintended public content.
From the tool's definition Tool fetches and retrieves content via GET requests only: 'Fetches the content of a URL and returns the extracted article content. Only supports GET requests.' No modification, deletion, or execution capabilities are described.
Attacks that exploit this kind of access
Fetches the content of a URL and returns the extracted article content. Only supports GET requests. Not suitable for debugging HTML. It is categorised as a Read tool in the Mcp Web MCP Server, which means it retrieves data without modifying state.
Register the Mcp Web MCP server in PolicyLayer and add a rule for fetch: 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 Web. Nothing to install.
fetch 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 fetch 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 fetch. 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.
fetch is provided by the Mcp Web MCP server (tsfreddie/mcp-web). 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 →