AI agents call web.fetch to retrieve information from TOOL4LM 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 protective measures against server-side request forgery. While network fetching carries some inherent risk (SSRF vulnerabilities, accessing unintended endpoints), the anti-SSRF protections and size/time limits mitigate misuse. The tool cannot modify data, execute code, or cause irreversible changes.
From the tool's definition Tool name is 'web.fetch' which retrieves content from a URL. Description states 'Fetch a URL' indicating a retrieval operation with built-in safety constraints ('size/time limits and anti-SSRF').
Attacks that exploit this kind of access
Fetch a URL with size/time limits and anti-SSRF. It is categorised as a Read tool in the TOOL4LM MCP Server, which means it retrieves data without modifying state.
Register the TOOL4LM MCP server in PolicyLayer and add a rule for web.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 TOOL4LM. Nothing to install.
web.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 web.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 web.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.
web.fetch is provided by the TOOL4LM MCP server (khanhs-234/tool4lm). 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 →