Gets the status of a Cloud SQL operation.
AI agents call get_csql_operation to retrieve information from Observability without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves operational status data from GCP Cloud SQL without modifying any resources or triggering side effects. It falls clearly into the Read category as it only queries existing state information. The severity is low because status checks have minimal blast radius and cannot cause harm even if misused.
From the tool's definition The tool name and description indicate it retrieves status information: 'Gets the status of a Cloud SQL operation.' This is a query/fetch operation with no modification, deletion, or execution of commands.
Attacks that exploit this kind of access
Gets the status of a Cloud SQL operation. It is categorised as a Read tool in the Observability MCP Server, which means it retrieves data without modifying state.
Register the Observability MCP server in PolicyLayer and add a rule for get_csql_operation: 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 Observability. Nothing to install.
get_csql_operation 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_csql_operation 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_csql_operation. 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_csql_operation is provided by the Observability MCP server (@google-cloud/observability-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 →