Fetch a URL through UnblockingAPI, bypassing bot detection, CAPTCHAs, and geo-blocks
AI agents call unblock_fetch to retrieve information from Unblockingapi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves web page content from a given URL — a read operation with no persistent side effects. Severity is medium because it bypasses anti-bot protections and geo-restrictions, meaning it could be misused to access restricted content, scrape protected sites, or circumvent access controls at scale.
From the tool's definition Fetch a URL through UnblockingAPI, bypassing bot detection, CAPTCHAs, and geo-blocks
Attacks that exploit this kind of access
Fetch a URL through UnblockingAPI, bypassing bot detection, CAPTCHAs, and geo-blocks. It is categorised as a Read tool in the Unblockingapi MCP Server, which means it retrieves data without modifying state.
Register the Unblockingapi MCP server in PolicyLayer and add a rule for unblock_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 Unblockingapi. Nothing to install.
unblock_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 unblock_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 unblock_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.
unblock_fetch is provided by the Unblockingapi MCP server (unblockingapi/mcp). 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 →