Capture screenshots at 100ms intervals for N seconds. Saves first frame + frame-count metadata.
AI agents call browser_record_trace to retrieve information from DevLab MCP Suite without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool only reads/captures visual state from the browser (screenshots) and saves metadata. It does not modify, execute, or delete any data. The only output is saved screenshot frames and metadata, which is a passive observation action similar to a screen capture or monitoring tool.
From the tool's definition Capture screenshots at 100ms intervals for N seconds. Saves first frame + frame-count metadata.
Attacks that exploit this kind of access
Capture screenshots at 100ms intervals for N seconds. Saves first frame + frame-count metadata. It is categorised as a Read tool in the DevLab MCP Suite MCP Server, which means it retrieves data without modifying state.
Register the DevLab MCP Suite MCP server in PolicyLayer and add a rule for browser_record_trace: 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 DevLab MCP Suite. Nothing to install.
browser_record_trace 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 browser_record_trace 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 browser_record_trace. 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.
browser_record_trace is provided by the DevLab MCP Suite MCP server (tanguito86/devlab-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 →