Push workflows to source control
AI agents use source_control_push 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.
This tool modifies a remote repository by pushing workflow changes, which is a reversible Write operation. It doesn't delete data (Destructive), execute arbitrary code (Execute), or move money (Financial). The severity is medium because pushing to source control could overwrite existing workflows or introduce malicious automation, but the change is version-controlled and can be reverted.
From the tool's definition Tool name 'source_control_push' and description 'Push workflows to source control' indicate it writes/commits data to a version control system.
Attacks that exploit this kind of access
Push workflows to 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_push: 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_push 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_push 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_push. 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_push 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 →