get_flows
AI agents call get_flows to retrieve information from Klaviyo MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves flow data from Klaviyo, likely returning existing marketing automation workflows or campaign flows. This is a non-destructive query operation with no side effects. The empty description slightly reduces confidence, but the name alone strongly indicates a read operation. Severity is low because retrieving marketing workflow metadata poses minimal risk even if misused by an AI agent.
From the tool's definition Tool name 'get_flows' indicates a retrieval operation. In the context of a marketing automation platform, 'get' operations fetch existing data without modification.
Attacks that exploit this kind of access
get_flows. It is categorised as a Read tool in the Klaviyo MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Klaviyo MCP Server MCP server in PolicyLayer and add a rule for get_flows: 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 Klaviyo MCP Server. Nothing to install.
get_flows 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 get_flows 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 get_flows. 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.
get_flows is provided by the Klaviyo MCP Server MCP server (ivan-rivera-projects/klaviyo-mcp-server-enhanced). 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 →