Returns an extra response
AI agents call extra_response to retrieve information from Debug Test without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to read or retrieve data (an 'extra response') without side effects. While the description is uninformative, the verb 'returns' and the context of a debug/test server suggest it retrieves information. No evidence indicates write, destructive, execute, or financial operations. Confidence is moderate due to the vague description, but the most defensible classification is Read with low severity.
From the tool's definition Tool name is 'extra_response' with description 'Returns an extra response'. The description is minimal, but 'Returns' indicates a retrieval operation with no modification, deletion, or execution of external commands.
Attacks that exploit this kind of access
Returns an extra response. It is categorised as a Read tool in the Debug Test MCP Server, which means it retrieves data without modifying state.
Register the Debug Test MCP server in PolicyLayer and add a rule for extra_response: 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 Debug Test. Nothing to install.
extra_response 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 extra_response 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 extra_response. 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.
extra_response is provided by the Debug Test MCP server (matsjfunke/debug-test-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 →