AI agents use approve_merge_request to create or update resources in GitLab MCP for Code Review — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GitLab MCP for Code Review environment.
Approving a merge request is a reversible write action (it can be unapproved, as evidenced by the sibling tool 'unapprove_merge_request'), but it carries high severity because an AI agent misusing it could approve malicious or low-quality code changes, potentially enabling harmful code to be merged into production branches.
From the tool's definition Tool name 'approve_merge_request'; server description states the server allows agents to 'approve/unapprove merge requests directly through the GitLab API'
Documented attack patterns abuse exactly the kind of access approve_merge_request gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and GitLab MCP for Code Review, and nothing reaches the server without passing your rules. This is the rule we recommend for approve_merge_request:
{
"version": "1",
"default": "deny",
"tools": {
"approve_merge_request": {
"limits": [
{
"counter": "approve_merge_request_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}approve_merge_request stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
approve_merge_request. It is categorised as a Write tool in the GitLab MCP for Code Review MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GitLab MCP for Code Review MCP server in PolicyLayer and add a rule for approve_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 GitLab MCP for Code Review. Nothing to install.
approve_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 approve_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 approve_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.
approve_merge_request is provided by the GitLab MCP for Code Review MCP server (mehmetakinn/gitlab-mcp-code-review). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from GitLab MCP for Code Review, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 GitLab MCP for Code Review tools catalogued and risk-classified — across an index of 43,000+ MCP servers.