AI agents call ami_lookup_xsec 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 appears designed to retrieve (lookup) cross-section physics data from a database, a read-only operation. The 'lookup' verb and the context of ATLAS physics research indicate data retrieval without modification. Confidence is slightly reduced due to the empty description, but the server's stated purpose and sibling tool patterns strongly suggest read-only functionality.
From the tool's definition Tool name 'ami_lookup_xsec' suggests querying cross-section data from the PMG database. Server description indicates metadata retrieval and data queries with 'no side effects' capability.
Attacks that exploit this kind of access
ami_lookup_xsec. 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_lookup_xsec: 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_lookup_xsec 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_lookup_xsec 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_lookup_xsec. 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_lookup_xsec 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 →