comment_on_issue
AI agents use comment_on_issue to create or update resources in Qodev Gitlab — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Qodev Gitlab environment.
This tool creates/adds data (a comment on a GitLab issue) without irreversible deletion, financial impact, or arbitrary code execution. It is reversible and has minimal blast radius. Write category is appropriate. Severity is low because commenting has limited negative impact; an AI agent misuse would result in unwanted comments that can be easily removed by a human administrator.
From the tool's definition Tool name 'comment_on_issue' indicates adding a comment to an issue. Sibling tools like 'comment_on_merge_request' and 'create_inline_comment' confirm this server supports comment creation.
Attacks that exploit this kind of access
comment_on_issue. It is categorised as a Write tool in the Qodev Gitlab MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Qodev Gitlab MCP server in PolicyLayer and add a rule for comment_on_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 Qodev Gitlab. Nothing to install.
comment_on_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 comment_on_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 comment_on_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.
comment_on_issue is provided by the Qodev Gitlab MCP server (qodevai/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 →