Fermer une issue. Par defaut dry_run=true : retourne un apercu sans fermer. Passer dry_run=false apres confirmation.
AI agents use close_issue to create or update resources in Mcp Gitlab — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Gitlab environment.
Closing an issue is a reversible state change (the issue can be reopened), not an irreversible deletion. This qualifies as Write rather than Destructive. Severity is medium because misuse could disrupt workflows by closing important issues, affecting team communication and project tracking, but the action is reversible.
From the tool's definition Tool name 'close_issue' and description 'Fermer une issue' (French: 'Close an issue') indicates state modification.
Attacks that exploit this kind of access
Fermer une issue. Par defaut dry_run=true : retourne un apercu sans fermer. Passer dry_run=false apres confirmation. It is categorised as a Write tool in the Mcp Gitlab MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Gitlab MCP server in PolicyLayer and add a rule for close_issue: 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 Mcp Gitlab. Nothing to install.
close_issue 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 close_issue 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 close_issue. 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.
close_issue is provided by the Mcp Gitlab MCP server (wanadev/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 →