debug_sdk_config
AI agents call debug_sdk_config to retrieve information from Looker Admin MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name suggests it reads or inspects SDK configuration for debugging purposes, which is a Read operation. However, the empty description significantly lowers confidence. Given the server context (Looker Admin MCP) and sibling tools like 'debug_network_connectivity' and 'health_check' which are diagnostic/read tools, it's reasonable to classify this as Read.
From the tool's definition Tool name 'debug_sdk_config' and empty description; 'debug' prefix typically implies inspection/reading of configuration rather than modification.
Attacks that exploit this kind of access
debug_sdk_config. It is categorised as a Read tool in the Looker Admin MCP MCP Server, which means it retrieves data without modifying state.
Register the Looker Admin MCP server in PolicyLayer and add a rule for debug_sdk_config: 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 Looker Admin MCP. Nothing to install.
debug_sdk_config 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 debug_sdk_config 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 debug_sdk_config. 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.
debug_sdk_config is provided by the Looker Admin MCP server (kokevidaurre/looker-admin-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 →