borrowip_fetch
AI agents invoke borrowip_fetch to trigger actions in BorrowIP MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Given the server context (web scraping via cellular SSH tunnels) and the 'fetch' name, this tool most likely retrieves remote web content by executing HTTP requests routed through a phone's cellular connection. This is an Execute-level action because it triggers external network operations whose effects depend on arguments (arbitrary URLs fetched through a proxy tunnel).
From the tool's definition Tool name 'borrowip_fetch' on a server designed to route web scraping traffic through SSH reverse tunnels using mobile IPs. Description is empty.
Attacks that exploit this kind of access
borrowip_fetch. It is categorised as a Execute tool in the BorrowIP MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the BorrowIP MCP Server MCP server in PolicyLayer and add a rule for borrowip_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 BorrowIP MCP Server. Nothing to install.
borrowip_fetch is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the borrowip_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 borrowip_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.
borrowip_fetch is provided by the BorrowIP MCP Server MCP server (wahyuzero/borrowip). 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 →