Fetch any URL through residential proxy (2M+ IPs, 195 countries, anti-bot bypass). Returns structured JSON with ok, data.content, data.status_code, meta.latency_ms, and meta.cache_hit. WHEN TO USE: Static/HTML pages, Amazon, LinkedIn, news sites, most commercial sites. USE agentproxy_render INST...
Accepts URL/endpoint input (url)
Part of the Bestproxy4agents MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call agentproxy_fetch 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_fetch 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.
tools:
agentproxy_fetch:
rules:
- action: allowSee the full Bestproxy4agents policy for all 8 tools.
Agents calling read-class tools like agentproxy_fetch have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Fetch any URL through residential proxy (2M+ IPs, 195 countries, anti-bot bypass). Returns structured JSON with ok, data.content, data.status_code, meta.latency_ms, and meta.cache_hit. WHEN TO USE: Static/HTML pages, Amazon, LinkedIn, news sites, most commercial sites. USE agentproxy_render INSTEAD IF: Page requires JavaScript to load (SPAs, React/Vue apps, dynamic feeds). USE agentproxy_extract INSTEAD IF: You need structured fields (title, price, rating) not raw content. ON FAILURE: If error.code is BOT_DETECTION_SUSPECTED → retry with agentproxy_render. If TLS_ERROR → retry with a different country parameter. CACHING: Repeated calls to the same URL+format+country are served from in-process cache (default TTL 300s). meta.cache_hit=true means no proxy credit was used. Sessions with session_id are never cached.. It is categorised as a Read tool in the Bestproxy4agents MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for agentproxy_fetch. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Bestproxy4agents MCP server.
agentproxy_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 agentproxy_fetch rule in your Intercept 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 Intercept policy for agentproxy_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.
agentproxy_fetch is provided by the Bestproxy4agents MCP server (bestproxy4agents-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept