Fetch latest OCI pricing from Oracle\
AI agents call refresh_oci_pricing to retrieve information from Cloud Cost MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool fetches (retrieves) pricing information from Oracle's OCI service. Fetching data is a Read operation with no side effects—it does not create, modify, delete data, execute arbitrary code, or commit financial obligations. The low severity reflects that misuse would only expose pricing data, which is typically public or semi-public information with minimal blast radius.
From the tool's definition Tool name 'refresh_oci_pricing' and description 'Fetch latest OCI pricing from Oracle' indicate a retrieval operation that queries current pricing data without modification, deletion, or execution of external code.
Attacks that exploit this kind of access
Fetch latest OCI pricing from Oracle\. It is categorised as a Read tool in the Cloud Cost MCP MCP Server, which means it retrieves data without modifying state.
Register the Cloud Cost MCP server in PolicyLayer and add a rule for refresh_oci_pricing: 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 Cloud Cost MCP. Nothing to install.
refresh_oci_pricing 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 refresh_oci_pricing 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 refresh_oci_pricing. 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.
refresh_oci_pricing is provided by the Cloud Cost MCP server (jasonwilbur/cloud-cost-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 →