browser_console_messages
AI agents call browser_console_messages to retrieve information from DevServer MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name indicates it retrieves or queries browser console messages—a passive data retrieval operation. Although the description is uninformative, the context of sibling Playwright-based browser tools suggests this reads console logs without modifying state. Confidence is moderate due to empty description, but the read-only semantics of 'console_messages' are clear.
From the tool's definition Tool name 'browser_console_messages' suggests retrieval of console output from browser automation context.
Attacks that exploit this kind of access
browser_console_messages. It is categorised as a Read tool in the DevServer MCP MCP Server, which means it retrieves data without modifying state.
Register the DevServer MCP server in PolicyLayer and add a rule for browser_console_messages: 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 DevServer MCP. Nothing to install.
browser_console_messages 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_console_messages 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_console_messages. 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_console_messages is provided by the DevServer MCP server (uninen/devserver-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 →