AI agents call ami_get_dataset_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.
This tool retrieves hashtag metadata associated with datasets—a read-only query operation with no side effects. The 'get_' prefix and absence of parameters suggesting modification/deletion indicate data retrieval. Confidence is reduced to 0.75 due to missing description, but the naming pattern and server context strongly suggest metadata lookup rather than modification or execution.
From the tool's definition Tool name 'ami_get_dataset_hashtags' indicates retrieval of hashtag metadata. The server context shows this is part of ATLAS metadata interface for MC sample discovery. Sibling tool 'ami_search_by_hashtags' confirms hashtags are queryable metadata.
Attacks that exploit this kind of access
ami_get_dataset_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_get_dataset_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_get_dataset_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_get_dataset_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_get_dataset_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_get_dataset_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 →