AI agents call ami_get_ami_tag to retrieve information from Ami without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about an AMI processing tag, which is a read-only query operation. It fits the Read category as it queries data without creating, modifying, deleting, or executing arbitrary operations. The low severity reflects minimal risk even if misused by an AI agent, as it only exposes informational data about processing tags in a physics experiment metadata system.
From the tool's definition Tool name 'ami_get_ami_tag' and description 'Get information about an AMI processing tag' indicate a retrieval operation with no data modification or side effects.
Attacks that exploit this kind of access
Get information about an AMI processing tag. It is categorised as a Read tool in the Ami MCP Server, which means it retrieves data without modifying state.
Register the Ami MCP server in PolicyLayer and add a rule for ami_get_ami_tag: 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 Ami. Nothing to install.
ami_get_ami_tag 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 ami_get_ami_tag 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 ami_get_ami_tag. 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.
ami_get_ami_tag is provided by the Ami MCP server (kratsg/ami-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 →