AI agents call ami_search_by_hashtags 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.
Searching datasets by hashtags is a retrieval operation that queries existing metadata without modifying, executing code, or deleting data. It fits the 'Read' category pattern of MC sample discovery and validation. Low severity because misuse would only retrieve unwanted metadata, with no destructive or computational consequences.
From the tool's definition Tool name 'ami_search_by_hashtags' indicates a search/query operation. The server's purpose is 'query the ATLAS Metadata Interface (AMI) and PMG cross-section database for MC sample discovery and metadata retrieval.' Sibling tools like 'ami_list_datasets',…
Attacks that exploit this kind of access
ami_search_by_hashtags. 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_search_by_hashtags: 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_search_by_hashtags 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_search_by_hashtags 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_search_by_hashtags. 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_search_by_hashtags 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 →