Create a new merge request in a GitLab project
AI agents use create_merge_request to create or update resources in Helm Chart CLI — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Helm Chart CLI environment.
This tool creates (writes) a new merge request artifact in GitLab, which is a standard git workflow object. While merge requests can trigger CI/CD pipelines or other automated processes, the direct action is creating/writing metadata in GitLab. The operation is reversible (the MR can be closed/deleted). It does not execute arbitrary code, delete data permanently, or move money.
From the tool's definition Tool name is 'create_merge_request' and description states it will 'Create a new merge request in a GitLab project'. This creates a new code review object in GitLab, which is a reversible modification to the version control system.
Attacks that exploit this kind of access
Create a new merge request in a GitLab project. It is categorised as a Write tool in the Helm Chart CLI MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Helm Chart CLI MCP server in PolicyLayer and add a rule for create_merge_request: 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 Helm Chart CLI. Nothing to install.
create_merge_request 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 create_merge_request 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 create_merge_request. 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.
create_merge_request is provided by the Helm Chart CLI MCP server (jeff-nasseri/servers). 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 →