合併 Merge Request
AI agents use merge_merge_request to create or update resources in GitLab MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GitLab MCP Server environment.
Merging a merge request creates or modifies repository state by integrating code changes into a branch. This is a Write operation rather than Execute because the tool performs a well-defined, bounded action (merge logic) rather than arbitrary code execution. It is reversible (via revert commits), distinguishing it from Destructive.
From the tool's definition Tool is named 'merge_merge_request' and merges (combines) a merge request into a target branch. The description '合併 Merge Request' translates to 'Merge Merge Request'.
Attacks that exploit this kind of access
合併 Merge Request. It is categorised as a Write tool in the GitLab MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GitLab MCP Server MCP server in PolicyLayer and add a rule for merge_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 Server. Nothing to install.
merge_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 merge_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 merge_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.
merge_merge_request is provided by the GitLab MCP Server MCP server (snowild/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 →