get_instance
AI agents call get_instance to retrieve information from OCI MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get_' prefix strongly indicates a read operation that queries and retrieves compute instance information from OCI. While the description is empty, context from sibling tools and the server's design pattern confirms this is a data retrieval operation with no side effects.
From the tool's definition Tool name 'get_instance' combined with sibling tools like 'get_alarm', 'get_autonomous_database', 'get_boot_volume', 'get_bucket', 'get_budget' all following a 'get_*' retrieval pattern, and the server's stated purpose of enabling interaction with OCI…
Attacks that exploit this kind of access
get_instance. It is categorised as a Read tool in the OCI MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OCI MCP Server MCP server in PolicyLayer and add a rule for get_instance: 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 OCI MCP Server. Nothing to install.
get_instance is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_instance 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 get_instance. 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.
get_instance is provided by the OCI MCP Server MCP server (jopsis/mcp-server-oci). 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 →