Get current errors and exceptions
AI agents call get-errors to retrieve information from Debugger MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries existing error and exception data from a debugging session. It performs no side effects, does not execute code, and does not modify any state. It is a pure read operation consistent with log inspection or diagnostic data retrieval in a debugger context.
From the tool's definition Tool name 'get-errors' and description 'Get current errors and exceptions' indicate retrieval of diagnostic information without modification or execution of code.
Attacks that exploit this kind of access
Get current errors and exceptions. It is categorised as a Read tool in the Debugger MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Debugger MCP Server MCP server in PolicyLayer and add a rule for get-errors: 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 Debugger MCP Server. Nothing to install.
get-errors 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-errors 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-errors. 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-errors is provided by the Debugger MCP Server MCP server (phoenixrr2113/debugger-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 →