Close a connection to a named Oracle database.
AI agents use disconnect to create or update resources in Oracle DB MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Oracle DB MCP Server environment.
Disconnecting a database connection is a connection management operation that alters session state reversibly. It does not delete data, execute queries, or trigger external operations. It ranks above Read because it modifies system state, but is less severe than Execute or Destructive because the primary data and logic remain unaffected.
From the tool's definition The tool closes ('disconnects') a connection to an Oracle database. Closing a connection modifies the state of the connection pool and active sessions, which is a reversible state change.
Attacks that exploit this kind of access
Close a connection to a named Oracle database. It is categorised as a Write tool in the Oracle DB MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Oracle DB MCP Server 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 Oracle DB MCP Server. 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 Oracle DB MCP Server MCP server (titan213/oracle-db-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 →