Extract structured fields (title, price, rating, author, etc.) from any URL via residential proxy. Returns JSON with ok, data.fields as key-value map. Uses Open Graph, JSON-LD, and HTML heuristics. WHEN TO USE: Product pages, articles, listings where you need specific fields not raw content. USE ...
Risk signalsAccepts URL/endpoint input (url)
Part of the Bestproxy4agents server.
Free to start. No card required.
AI agents call agentproxy_extract to retrieve information from Bestproxy4agents without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though agentproxy_extract only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"agentproxy_extract": {}
}
}See the full Bestproxy4agents policy for all 8 tools.
These attack patterns abuse exactly the kind of access agentproxy_extract gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Extract structured fields (title, price, rating, author, etc.) from any URL via residential proxy. Returns JSON with ok, data.fields as key-value map. Uses Open Graph, JSON-LD, and HTML heuristics. WHEN TO USE: Product pages, articles, listings where you need specific fields not raw content. USE agentproxy_fetch INSTEAD IF: You need full page content, not specific fields. AUTO-ESCALATION: Set render_fallback:true to automatically retry via real browser (agentproxy_render) if the proxy fetch fails with TLS_ERROR or bot detection. Costs 5 credits if escalated. ON FAILURE without render_fallback: If TLS_ERROR or BOT_DETECTION_SUSPECTED → retry with render_fallback:true.. It is categorised as a Read tool in the Bestproxy4agents MCP Server, which means it retrieves data without modifying state.
Register the Bestproxy4agents MCP server in PolicyLayer and add a rule for agentproxy_extract: 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 Bestproxy4agents. Nothing to install.
agentproxy_extract 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 agentproxy_extract 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 agentproxy_extract. 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.
agentproxy_extract is provided by the Bestproxy4agents MCP server (bestproxy4agents-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 8 Bestproxy4agents tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.