Gets a console message by its ID. You can get all messages by calling ${LIST_CONSOLE_MESSAGES_TOOL_NAME}.
AI agents call get_console_message to retrieve information from Opera DevTools MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves console messages from the DevTools without modifying, executing, or deleting anything. It is purely informational—a read operation that queries existing console output. The severity is low as misuse would only expose potentially sensitive information already logged to the console, with no capability to alter system state or trigger external operations.
From the tool's definition Tool name 'get_console_message' and description 'Gets a console message by its ID' indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Gets a console message by its ID. You can get all messages by calling ${LIST_CONSOLE_MESSAGES_TOOL_NAME}. It is categorised as a Read tool in the Opera DevTools MCP MCP Server, which means it retrieves data without modifying state.
Register the Opera DevTools MCP server in PolicyLayer and add a rule for get_console_message: 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 Opera DevTools MCP. Nothing to install.
get_console_message 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 get_console_message 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 get_console_message. 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.
get_console_message is provided by the Opera DevTools MCP server (operasoftware/opera-devtools-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 →