AI agents call search_requests to retrieve information from Proxypin without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and filters existing network traffic data based on URL keywords, HTTP methods, and status codes. It performs no writes, deletions, code execution, or financial operations. The blast radius of misuse is limited to potential exposure of intercepted HTTP(S) traffic metadata, which is already captured by the proxy. No irreversible actions are possible.
From the tool's definition Tool description indicates 'Filter captured traffic' and 'search' operations without any modification or deletion of data.
Attacks that exploit this kind of access
Filter captured traffic by URL keyword, HTTP method, and/or status code. Supports combining filters (e.g. keyword=. It is categorised as a Read tool in the Proxypin MCP Server, which means it retrieves data without modifying state.
Register the Proxypin MCP server in PolicyLayer and add a rule for search_requests: 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 Proxypin. Nothing to install.
search_requests 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 search_requests 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 search_requests. 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.
search_requests is provided by the Proxypin MCP server (k186/proxypin-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 →