Approve or reject a Percy build
AI agents use managePercyBuildApproval to create or update resources in BrowserStack — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your BrowserStack environment.
This tool modifies the approval state of a Percy build (visual testing), which is a reversible change. It does not execute tests, delete data irreversibly, or move money. The blast radius is moderate—approving/rejecting builds can affect deployment workflows and test result visibility, but changes can be undone by re-approving or re-rejecting.
From the tool's definition Tool name 'managePercyBuildApproval' and description 'Approve or reject a Percy build' indicate state changes to build approval status in a testing/CI pipeline.
Attacks that exploit this kind of access
Approve or reject a Percy build. It is categorised as a Write tool in the BrowserStack MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the BrowserStack MCP server in PolicyLayer and add a rule for managePercyBuildApproval: 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 BrowserStack. Nothing to install.
managePercyBuildApproval 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 managePercyBuildApproval 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 managePercyBuildApproval. 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.
managePercyBuildApproval is provided by the BrowserStack MCP server (browserstack/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.