Возвращает список узлов для указанной категории.
AI agents call get_nodes_by_category to retrieve information from n8n MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns node metadata for a given category. It performs no writes, deletions, or external operations—purely informational retrieval. The read-only nature and lack of state modification make it low-severity. The sibling tools on this server include destructive operations (delete_workflow, execute_workflow), but this specific tool has no side effects.
From the tool's definition Tool name 'get_nodes_by_category' and description 'Returns a list of nodes for the specified category' indicate retrieval of node information without side effects.
Attacks that exploit this kind of access
Возвращает список узлов для указанной категории. It is categorised as a Read tool in the n8n MCP Server MCP Server, which means it retrieves data without modifying state.
Register the n8n MCP Server MCP server in PolicyLayer and add a rule for get_nodes_by_category: 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 n8n MCP Server. Nothing to install.
get_nodes_by_category 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_by_category 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_by_category. 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_by_category is provided by the n8n MCP Server MCP server (ospray-creator/n8n-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 →