AI agents call iac_pulumi_stacks to retrieve information from Infra Ops without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a query/list operation to retrieve infrastructure-as-code stack information. It retrieves data about Pulumi stacks without creating, modifying, executing, or deleting anything. While the sibling tools on this infra-ops server include destructive capabilities (like EC2 and RDS management), this specific tool is limited to information retrieval.
From the tool's definition Tool name 'iac_pulumi_stacks' and description 'List all Pulumi stacks in JSON format' indicate a retrieval operation with no modification or execution capability.
Attacks that exploit this kind of access
List all Pulumi stacks in JSON format. It is categorised as a Read tool in the Infra Ops MCP Server, which means it retrieves data without modifying state.
Register the Infra Ops MCP server in PolicyLayer and add a rule for iac_pulumi_stacks: 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 Infra Ops. Nothing to install.
iac_pulumi_stacks 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 iac_pulumi_stacks 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 iac_pulumi_stacks. 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.
iac_pulumi_stacks is provided by the Infra Ops MCP server (skyvanguard/infra-ops-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 →