AI agents call read_crash_report to retrieve information from Console without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves crash report data for debugging purposes. It has no side effects, cannot modify or delete data, and does not execute code or commands. It is a straightforward query/retrieval operation consistent with the Read category. The severity is low because exposure of crash logs may reveal system debugging information but does not enable destructive or financial harm.
From the tool's definition Tool name 'read_crash_report' and description 'Read the full content of a specific crash report' explicitly indicate retrieval of existing data without modification.
Attacks that exploit this kind of access
Read the full content of a specific crash report. It is categorised as a Read tool in the Console MCP Server, which means it retrieves data without modifying state.
Register the Console MCP server in PolicyLayer and add a rule for read_crash_report: 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 Console. Nothing to install.
read_crash_report 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 read_crash_report 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 read_crash_report. 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.
read_crash_report is provided by the Console MCP server (rohithgoud30/console-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 →