Pull workflows from source control
AI agents use source_control_pull to create or update resources in N8n Fabric — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your N8n Fabric environment.
Pulling from source control retrieves remote workflow definitions and writes/overwrites them into the local n8n instance. This is a write operation (it modifies the local state of workflows) but is generally reversible by pulling a different version. It is not purely destructive since source control history is preserved, but it does overwrite existing workflow definitions in the system.
From the tool's definition Pull workflows from source control
Attacks that exploit this kind of access
Pull workflows from source control. It is categorised as a Write tool in the N8n Fabric MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the N8n Fabric MCP server in PolicyLayer and add a rule for source_control_pull: 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.
source_control_pull is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the source_control_pull 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 source_control_pull. 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.
source_control_pull 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 →