AI agents invoke rebase_merge_request to trigger actions in Gitlab. 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.
Rebasing a merge request triggers a git rebase operation on the server side, which modifies commit history and applies changes onto the target branch. This is an external operation with side effects beyond simple data writes — it rewrites commit history, which can be difficult to reverse, though it's not strictly a destructive delete.
From the tool's definition Rebase a merge request onto the target branch
Documented attack patterns abuse exactly the kind of access rebase_merge_request gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Gitlab, and nothing reaches the server without passing your rules. This is the rule we recommend for rebase_merge_request:
{
"version": "1",
"default": "deny",
"tools": {
"rebase_merge_request": {
"limits": [
{
"counter": "rebase_merge_request_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}rebase_merge_request stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Rebase a merge request onto the target branch. It is categorised as a Execute tool in the Gitlab MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Gitlab MCP server in PolicyLayer and add a rule for rebase_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. Nothing to install.
rebase_merge_request 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 rebase_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 rebase_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.
rebase_merge_request is provided by the Gitlab MCP server (yoda-digital/mcp-gitlab-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 88 Gitlab tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
88 Gitlab tools catalogued and risk-classified — across an index of 42,500+ MCP servers.