AI agents call get_current_connection to retrieve information from Postgres without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and reports the current state of the database connection. It has no side effects, does not execute queries, and does not modify any data. It is a safe diagnostic utility for checking connection parameters before other operations.
From the tool's definition Tool returns connection metadata: 'server name, database, schema, and access mode'. No modification, deletion, or execution of code occurs. It is purely informational—'Call this to verify your connection before running queries.'
Attacks that exploit this kind of access
Get current connection status. Returns server name, database, schema, and access mode (readonly/full). Call this to verify your connection before running queries. It is categorised as a Read tool in the Postgres MCP Server, which means it retrieves data without modifying state.
Register the Postgres MCP server in PolicyLayer and add a rule for get_current_connection: 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 Postgres. Nothing to install.
get_current_connection 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_current_connection 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_current_connection. 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_current_connection is provided by the Postgres MCP server (teja-sudo/postgres-mcp-server). 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 →