获取浏览器网络请求记录
AI agents call get_network_requests to retrieve information from MCP Browser Logger without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns historical network request logs from the browser, similar to inspecting DevTools Network tab. It reads existing data with no side effects, no code execution, and no state modification. While network data can be sensitive (URLs, headers, payloads), the tool itself performs only passive inspection.
From the tool's definition get_network_requests retrieves browser network request records. The description '获取浏览器网络请求记录' translates to 'get browser network request records', and the method name begins with 'get_', indicating data retrieval without modification.
Attacks that exploit this kind of access
获取浏览器网络请求记录. It is categorised as a Read tool in the MCP Browser Logger MCP Server, which means it retrieves data without modifying state.
Register the MCP Browser Logger MCP server in PolicyLayer and add a rule for get_network_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 MCP Browser Logger. Nothing to install.
get_network_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 get_network_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 get_network_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.
get_network_requests is provided by the MCP Browser Logger MCP server (tao-lionel/mcp-browser-logger). 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 →