Select which browser to use when multiple are installed.
AI agents use select_browser to create or update resources in Chromium Sync — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Chromium Sync environment.
This tool modifies the active configuration/state by selecting which browser to use. It doesn't retrieve data (Read), execute commands, delete anything, or move money. It changes a persistent setting (which browser profile path is used), making Write the most appropriate category. Severity is low since misconfiguration only affects which browser's data is accessed, not data integrity itself.
From the tool's definition Select which browser to use when multiple are installed.
Attacks that exploit this kind of access
Select which browser to use when multiple are installed. It is categorised as a Write tool in the Chromium Sync MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Chromium Sync MCP server in PolicyLayer and add a rule for select_browser: 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 Chromium Sync. Nothing to install.
select_browser 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 select_browser 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 select_browser. 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.
select_browser is provided by the Chromium Sync MCP server (jaidhyani/chromium-sync-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 →