AI agents call connection-status to retrieve information from Sql without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only queries and reports the state of the database connection and the current query mode setting. It is a pure informational read operation with no side effects, data modification, or execution capability. The low severity reflects that misuse poses minimal risk—an agent cannot cause harm by checking connection status.
From the tool's definition The tool name is 'connection-status' and description states it 'Check[s] the current database connection status and query mode.' This retrieves connection metadata without modifying data, executing queries, or triggering side effects.
Attacks that exploit this kind of access
Check the current database connection status and query mode. It is categorised as a Read tool in the Sql MCP Server, which means it retrieves data without modifying state.
Register the Sql MCP server in PolicyLayer and add a rule for connection-status: 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 Sql. Nothing to install.
connection-status 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 connection-status 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 connection-status. 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.
connection-status is provided by the Sql MCP server (nakiriyuuzu/sql-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 →