// MCP TOOL REFERENCE

oci_adb_stop

Stop a running Autonomous Database

Free to start. No card required.

WHEN AGENTS USE THIS TOOL

AI agents invoke oci_adb_stop to trigger processes or run actions in Oracle Cloud. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.

oci_adb_stop can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.

RECOMMENDED POLICY

Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "oci_adb_stop": {
      "limits": [
        {
          "counter": "oci_adb_stop_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

See the full Oracle Cloud policy for all 23 tools.

MORE ORACLE CLOUD TOOLS

Destructive oci_compute_instance_action Destructive oci_os_delete_bucket Execute oci_adb_start Write oci_os_create_bucket Write oci_vcn_create Read oci_adb_get Read oci_adb_list Read oci_bv_list_boot_volumes

View all 23 tools →

WHAT CAN GO WRONG

These attack patterns abuse exactly the kind of access oci_adb_stop gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

OTHER EXECUTE TOOLS

Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.

Atv build_stake_tx Atv build_unstake_tx Docs Mcp answer_how_to Acdp start_local Pentagonal pentagonal_audit Pentagonal pentagonal_compile

FAQ

What does the oci_adb_stop tool do? +

Stop a running Autonomous Database. It is categorised as a Execute tool in the Oracle Cloud MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on oci_adb_stop? +

Register the Oracle Cloud MCP server in PolicyLayer and add a rule for oci_adb_stop: 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 Cloud. Nothing to install.

What risk level is oci_adb_stop? +

oci_adb_stop is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit oci_adb_stop? +

Yes. Add a rate_limit block to the oci_adb_stop 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 oci_adb_stop completely? +

Set action: deny in the PolicyLayer policy for oci_adb_stop. 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 oci_adb_stop? +

oci_adb_stop is provided by the Oracle Cloud MCP server (oracle-cloud-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Oracle Cloud tool call.

Deterministic rules across all 23 Oracle Cloud tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

SECURE ORACLE CLOUD →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

oci_adb_stop

// WHEN AGENTS USE THIS TOOL

// RECOMMENDED POLICY

// MORE ORACLE CLOUD TOOLS

// WHAT CAN GO WRONG

// OTHER EXECUTE TOOLS

// RELATED READING

// FAQ