Manage PostgreSQL connections: list active, kill idle, view stats.
AI agents invoke pg_connections to trigger actions in RedisNexus. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
While the tool includes read operations (list active, view stats), the 'kill idle' capability elevates the risk category significantly. Killing PostgreSQL connections is a destructive, disruptive action that terminates active sessions, potentially interrupting in-flight transactions and causing application errors.
From the tool's definition 'kill idle' connections — terminating active database connections is an irreversible disruptive action that can interrupt running transactions and application sessions
Attacks that exploit this kind of access
Manage PostgreSQL connections: list active, kill idle, view stats. It is categorised as a Execute tool in the RedisNexus MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the RedisNexus MCP server in PolicyLayer and add a rule for pg_connections: 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 RedisNexus. Nothing to install.
pg_connections is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the pg_connections 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 pg_connections. 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.
pg_connections is provided by the RedisNexus MCP server (rajkumar-madhu/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 →