Medium Risk

disconnect

Close a specific database connection and remove it from the pool. Args: conn_id: Connection ID to disconnect (required) ctx: Request context (injected by the framework) Returns: Dictionary indicating success status

How to control disconnect ↓

AI agents use disconnect to create or update resources in Pg — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pg environment.

Medium Risk

This tool modifies the connection pool state (removes a connection) rather than deleting data. It is reversible (reconnection is possible) and has no permanent side effects on the database itself. It ranks as Write rather than Destructive because the action is not irreversible.

From the tool's definition The tool 'disconnects' a database connection by removing it from the pool. While it modifies state (connection pool management), it does not delete data or execute queries. It's a reversible state change—a new connection can be established.

Documented attack patterns abuse exactly the kind of access disconnect gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and Pg, and nothing reaches the server without passing your rules. This is the rule we recommend for disconnect:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "disconnect": {
      "limits": [
        {
          "counter": "disconnect_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

disconnect stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Pg — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Go deeper

What does the disconnect tool do? +

Close a specific database connection and remove it from the pool. Args: conn_id: Connection ID to disconnect (required) ctx: Request context (injected by the framework) Returns: Dictionary indicating success status. It is categorised as a Write tool in the Pg MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on disconnect? +

Register the Pg MCP server in PolicyLayer and add a rule for disconnect: 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 Pg. Nothing to install.

What risk level is disconnect? +

disconnect is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit disconnect? +

Yes. Add a rate_limit block to the disconnect 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.

How do I block disconnect completely? +

Set action: deny in the PolicyLayer policy for disconnect. 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.

What MCP server provides disconnect? +

disconnect is provided by the Pg MCP server (stuzero/pg-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Pg tool call.

Deterministic rules across all 5 Pg tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

5 Pg tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.