retrieves browser diagnostics (console logs, JS errors, or network activity) captured via WebDriver BiDi
AI agents call diagnostics to retrieve information from Mcp Selenium without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a passive diagnostic retrieval tool that gathers observational data from the browser (console logs, JS errors, network activity) without modifying state, executing arbitrary code, or causing side effects. It functions purely as a reader of existing browser telemetry captured via WebDriver BiDi.
From the tool's definition Tool explicitly 'retrieves browser diagnostics' - retrieves, not executes or modifies. Captures read-only telemetry: console logs, JS errors, network activity.
Attacks that exploit this kind of access
retrieves browser diagnostics (console logs, JS errors, or network activity) captured via WebDriver BiDi. It is categorised as a Read tool in the Mcp Selenium MCP Server, which means it retrieves data without modifying state.
Register the Mcp Selenium MCP server in PolicyLayer and add a rule for diagnostics: 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 Mcp Selenium. Nothing to install.
diagnostics 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 diagnostics 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 diagnostics. 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.
diagnostics is provided by the Mcp Selenium MCP server (@angiejones/mcp-selenium). 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 →