get_avm_outputs
AI agents call get_avm_outputs to retrieve information from Azure Terraform MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to retrieve AVM output information for informational purposes. There is no indication it modifies, executes code, deletes, or moves money. The 'get_' prefix and '_outputs' suffix are consistent with read-only operations that query existing module metadata. Low severity reflects minimal blast radius if misused—an agent requesting AVM outputs would only retrieve information.
From the tool's definition Tool name 'get_avm_outputs' indicates retrieval of outputs from Azure Verified Modules (AVM). The sibling tools on this server include documentation retrieval ('get_avm_latest_version'), export operations ('export_azure_resource'), and validation tools…
Attacks that exploit this kind of access
get_avm_outputs. It is categorised as a Read tool in the Azure Terraform MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Azure Terraform MCP Server MCP server in PolicyLayer and add a rule for get_avm_outputs: 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 Azure Terraform MCP Server. Nothing to install.
get_avm_outputs 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_avm_outputs 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_avm_outputs. 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_avm_outputs is provided by the Azure Terraform MCP Server MCP server (liuwuliuyun/tf-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 →