AI agents call connection_status to retrieve information from Db Oauth without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Connection status checks are informational queries with no side effects. The server emphasizes 'read-only SQL queries' and OAuth security. This tool fits the Read category as it retrieves state information without creating, modifying, deleting, or executing operations. Low severity because status checks have minimal blast radius even if misused.
From the tool's definition Tool name 'connection_status' and description indicate checking connection state ('Show whether you'). This is a read-only operation that queries status without modifying data or executing commands.
Attacks that exploit this kind of access
Show whether you. It is categorised as a Read tool in the Db Oauth MCP Server, which means it retrieves data without modifying state.
Register the Db Oauth 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 Db Oauth. 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 Db Oauth MCP server (kpconnell/db-oauth-mcp-node). 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 →