Get execution details including input/output data
AI agents call execution_get to retrieve information from N8n Fabric without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read operation that retrieves execution details. However, severity is elevated to 'medium' rather than 'low' because execution data in n8n workflows may contain sensitive information (credentials, API keys, PII, business logic outputs), and unauthorized read access could expose secrets or confidential process information. The tool does not modify, delete, or execute anything—it only fetches existing data.
From the tool's definition Tool name 'execution_get' and description 'Get execution details including input/output data' indicate retrieval of execution metadata and results without modification or deletion.
Attacks that exploit this kind of access
Get execution details including input/output data. It is categorised as a Read tool in the N8n Fabric MCP Server, which means it retrieves data without modifying state.
Register the N8n Fabric MCP server in PolicyLayer and add a rule for execution_get: 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 Fabric. Nothing to install.
execution_get 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 execution_get 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 execution_get. 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.
execution_get is provided by the N8n Fabric MCP server (ry-ops/n8n-fabric). 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 →