AI agents invoke source_control_pull to trigger actions in N8n. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Pulling from a Git repository triggers an external operation that modifies the local n8n environment by applying remote changes (workflows, credentials, configurations) from the repository. This is not a simple write/create operation—it executes a Git pull which can overwrite existing workflows and settings in a potentially irreversible way.
From the tool's definition Pull changes from the connected Git repository
Attacks that exploit this kind of access
Pull changes from the connected Git repository. Requires write_mode and source control configured. It is categorised as a Execute tool in the N8n MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the N8n 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. Nothing to install.
source_control_pull is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
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 MCP server (siddharth0903/n8n-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 →