AI agents call get-nodes 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 'get-nodes' and the pattern of sibling tools (all prefixed with 'get-' or 'find-') strongly suggest this retrieves node information from Node-RED without modification. While the description is empty, the naming convention and context within the server make it highly likely this is a read operation querying available nodes.
From the tool's definition Tool name 'get-nodes' combined with sibling tools like 'find-nodes-by-type', 'get-node-info', 'get-flow', and 'get-flows' that are clearly retrieval operations. The 'get-' prefix is a strong indicator of read-only data retrieval.
Attacks that exploit this kind of access
get-nodes. 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-nodes: 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-nodes 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-nodes 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-nodes. 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-nodes 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 →