Discovers all internal skills available within the Kernels.
AI agents call list_expert_skills to retrieve information from n8n Architect MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation that lists or discovers internal skills. It has no side effects—it merely surfaces available capabilities for introspection. The word 'discovers' and 'available' clearly indicate a retrieval operation. Even in the context of an orchestration server managing workflows, listing skills is a passive information-gathering action with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'list_expert_skills' and description 'Discovers all internal skills available within the Kernels' indicate a query/discovery operation that retrieves information about available capabilities without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
Discovers all internal skills available within the Kernels. It is categorised as a Read tool in the n8n Architect MCP Server MCP Server, which means it retrieves data without modifying state.
Register the n8n Architect MCP Server MCP server in PolicyLayer and add a rule for list_expert_skills: 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 Architect MCP Server. Nothing to install.
list_expert_skills 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 list_expert_skills 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 list_expert_skills. 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.
list_expert_skills is provided by the n8n Architect MCP Server MCP server (srandres629/n8n_dev_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 →