create_merge_request
AI agents use create_merge_request to create or update resources in Qodev Gitlab — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Qodev Gitlab environment.
Creating a merge request is a reversible write operation that modifies repository state by introducing a new code review artifact. It does not delete data (Destructive), move money (Financial), or execute arbitrary code (Execute)—though merge requests can trigger CI/CD pipelines, the tool itself just creates the request object.
From the tool's definition Tool name is 'create_merge_request' which creates a new merge request in GitLab. Description is empty, but the name and context (GitLab MCP server for managing merge requests) clearly indicate this creates new data.
Attacks that exploit this kind of access
create_merge_request. It is categorised as a Write tool in the Qodev Gitlab MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Qodev Gitlab 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 Qodev Gitlab. 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 Qodev Gitlab MCP server (qodevai/gitlab-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 →