AI agents call ami_get_physics_params 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.
The 'get' prefix and the pattern of sibling tools (ami_get_ami_tag, ami_get_dataset_info, ami_get_dataset_prov, ami_lookup_xsec, ami_list_datasets, etc.) all perform read-only queries on metadata. This tool likely retrieves physics parameters associated with MC samples. No evidence suggests it modifies data, executes arbitrary code, deletes data, or involves financial transactions.
From the tool's definition Tool name 'ami_get_physics_params' with 'get' prefix indicates a retrieval operation. Description is empty, limiting certainty, but the naming convention and context of sibling tools (all ami_get_* and ami_list_* tools are query/retrieval operations on ATLAS…
Attacks that exploit this kind of access
ami_get_physics_params. 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_physics_params: 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_physics_params 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_physics_params 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_physics_params. 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_physics_params 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 →