list_available_os_images
AI agents call list_available_os_images to retrieve information from Nebulablock without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool lists available OS images—a read-only enumeration with no side effects. It queries data without creating, modifying, deleting, executing, or committing financial actions. The empty description lowers confidence slightly, but the name and sibling context (instance management, querying) strongly support Read classification.
From the tool's definition Tool name 'list_available_os_images' and context of sibling tools (get_computing_products, get_user_instances, get_user_instance_detail) indicate this retrieves/enumerates available OS image options.
Attacks that exploit this kind of access
list_available_os_images. It is categorised as a Read tool in the Nebulablock MCP Server, which means it retrieves data without modifying state.
Register the Nebulablock MCP server in PolicyLayer and add a rule for list_available_os_images: 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 Nebulablock. Nothing to install.
list_available_os_images 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 list_available_os_images 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 list_available_os_images. 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.
list_available_os_images is provided by the Nebulablock MCP server (nebula-block-data/nebulablock-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 →