AI agents use set_user_agent to create or update resources in InSite — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your InSite environment.
This tool modifies the browser's user agent configuration, which is a reversible write operation. Misuse could allow an AI agent to impersonate different browsers or devices, potentially bypassing security controls or user-agent-based restrictions during automated browsing sessions.
From the tool's definition Set the browser user agent string
Attacks that exploit this kind of access
Set the browser user agent string. It is categorised as a Write tool in the InSite MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the InSite MCP server in PolicyLayer and add a rule for set_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 InSite. Nothing to install.
set_user_agent is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the set_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 set_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.
set_user_agent is provided by the InSite MCP server (jowharshamshiri/insite). 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 →