AI agents call get-flows-state to retrieve information from Node Red without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name suggests it retrieves the current state of Node-RED flows without modifying them. While the description is empty (which slightly lowers confidence), the naming convention and context of sibling read-only 'get-*' tools indicate this is a non-destructive query operation. The blast radius is minimal since no data modification, execution, or deletion is possible.
From the tool's definition Tool name 'get-flows-state' indicates a retrieval operation. No description provided, but the naming pattern aligns with other read-only tools on this server like 'get-diagnostics', 'get-flow', 'get-flows', and 'get-node-info'.
Attacks that exploit this kind of access
get-flows-state. It is categorised as a Read tool in the Node Red MCP Server, which means it retrieves data without modifying state.
Register the Node Red MCP server in PolicyLayer and add a rule for get-flows-state: 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 Node Red. Nothing to install.
get-flows-state 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-state 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-state. 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-state is provided by the Node Red MCP server (node-red-mcp-server). 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 →