Fetch content from a URL. Supports http and https schemes.
AI agents call fetch_url to retrieve information from Vulnerable MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves content from URLs, which is fundamentally a Read operation. However, in the context of a deliberately insecure pentest server alongside tools like execute_system_command and proxy_request, this tool poses high risk: it could be abused for Server-Side Request Forgery (SSRF) attacks, allowing an AI agent to probe internal network resources, access cloud metadata endpoints (e.g., 169.254.169.254), or…
From the tool's definition Fetch content from a URL. Supports http and https schemes.
Attacks that exploit this kind of access
Fetch content from a URL. Supports http and https schemes. It is categorised as a Read tool in the Vulnerable MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Vulnerable MCP Server MCP server in PolicyLayer and add a rule for fetch_url: 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 Vulnerable MCP Server. Nothing to install.
fetch_url 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_url 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_url. 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_url is provided by the Vulnerable MCP Server MCP server (joyghoshs/vulnerable-mcp-server). 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 →