Ajouter un commentaire sur une issue. Par defaut dry_run=true.
AI agents use add_issue_note 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.
Adding a note/comment to an issue creates new data in a reversible manner (comments can be edited or deleted by authorized users), fitting the Write category. Severity is medium because while comment creation is not destructive, it affects issue tracking and team communication, and a malicious agent could spam or post misleading comments.
From the tool's definition Tool name 'add_issue_note' and description 'Ajouter un commentaire sur une issue' (Add a comment on an issue) directly indicates creation of new comment data on an existing issue. The server description mentions 'dry-run safety' as a built-in control.
Attacks that exploit this kind of access
Ajouter un commentaire sur une issue. Par defaut dry_run=true. 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 add_issue_note: 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.
add_issue_note 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 add_issue_note 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 add_issue_note. 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.
add_issue_note 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 →