unapprove_merge_request
AI agents use unapprove_merge_request to create or update resources in Kepler MCP GitLab Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kepler MCP GitLab Server environment.
Unapproving a merge request is a write operation that modifies merge request state/metadata without permanently deleting or destroying data. It is reversible—an approval can be re-added. This is less severe than destructive operations (which cannot be undone) but more severe than read operations.
From the tool's definition Tool name 'unapprove_merge_request' indicates it modifies the approval state of a merge request, a reversible change to repository metadata. Description is empty, limiting evidence.
Attacks that exploit this kind of access
unapprove_merge_request. It is categorised as a Write tool in the Kepler MCP GitLab Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kepler MCP GitLab Server MCP server in PolicyLayer and add a rule for unapprove_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 Kepler MCP GitLab Server. Nothing to install.
unapprove_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 unapprove_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 unapprove_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.
unapprove_merge_request is provided by the Kepler MCP GitLab Server MCP server (ryan-rbw/kepler-mcp-gitlab-server). 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 →