AI agents call parse_user_agent to retrieve information from Lkx without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool parses a User-Agent string to extract device and browser metadata. This is a pure read/analysis operation with no side effects, no data modification, and no external system interaction. Misuse potential is minimal as it only processes input strings locally.
From the tool's definition 解析浏览器 User-Agent 字符串，提取设备型号、系统版本、分辨率、网络类型等信息
Attacks that exploit this kind of access
解析浏览器 User-Agent 字符串，提取设备型号、系统版本、分辨率、网络类型等信息. It is categorised as a Read tool in the Lkx MCP Server, which means it retrieves data without modifying state.
Register the Lkx MCP server in PolicyLayer and add a rule for parse_user_agent: 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 Lkx. Nothing to install.
parse_user_agent 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 parse_user_agent 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 parse_user_agent. 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.
parse_user_agent is provided by the Lkx MCP server (liukexina/lkx-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 →