Connect (or switch) to an Oracle database. Three modes: - tns: Use a TNS alias from tnsnames.ora (run oracle_list_tns_entries first) - connection_string: Use a full TNS connect string - manual: Specify host, port, and service_name directly Closes any existing connection and opens a new pool. Afte...
AI agents invoke oracle_connect to trigger actions in Oracle APEX MCP Server. 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.
This tool actively manages database connection state: it terminates existing connections and establishes new ones to potentially different databases. This is an Execute-category action because it triggers external operations (network connections, pool management) whose effects depend on arguments (host, port, service_name, TNS alias).
From the tool's definition 'Closes any existing connection and opens a new pool' and 'Connect (or switch) to an Oracle database' — triggers external connection operations, closes existing state, and establishes new database connectivity
Attacks that exploit this kind of access
Connect (or switch) to an Oracle database. Three modes: - tns: Use a TNS alias from tnsnames.ora (run oracle_list_tns_entries first) - connection_string: Use a full TNS connect string - manual: Specify host, port, and service_name directly Closes any existing connection and opens a new pool. After connecting, runs a health check to verify. It is categorised as a Execute tool in the Oracle APEX MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Oracle APEX MCP Server MCP server in PolicyLayer and add a rule for oracle_connect: 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 APEX MCP Server. Nothing to install.
oracle_connect 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 oracle_connect 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 oracle_connect. 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.
oracle_connect is provided by the Oracle APEX MCP Server MCP server (silviosotelo/oracle-apex-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 →