AI agents use disconnect to create or update resources in Db Oauth — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Db Oauth environment.
Disconnecting from database connections and revoking access tokens modifies the authentication state but does not delete data or execute arbitrary operations. The action is reversible (user can reconnect). However, it affects active sessions for potentially multiple users if the server manages shared connections, warranting medium severity.
From the tool's definition Tool name 'disconnect' with description 'Disconnect from all database connections. Revokes the current access token' indicates state modification—terminating active sessions and invalidating credentials.
Attacks that exploit this kind of access
Disconnect from all database connections. Revokes the current access token and. It is categorised as a Write tool in the Db Oauth MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Db Oauth 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 Db Oauth. Nothing to install.
disconnect is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
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.
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.
disconnect 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 →