create_inline_comment
AI agents use create_inline_comment 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.
The tool creates (writes) a new inline comment, a reversible operation that modifies a merge request or code review by adding commentary. This is categorized as Write rather than Read (retrieves data) or Execute (triggers external operations with unpredictable effects). While the description is empty, the tool name and server context provide sufficient justification.
From the tool's definition Tool name 'create_inline_comment' indicates creation of comment data. Sibling tools like 'comment_on_issue' and 'comment_on_merge_request' establish that this server creates comments.
Attacks that exploit this kind of access
create_inline_comment. 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 create_inline_comment: 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.
create_inline_comment 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 create_inline_comment 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 create_inline_comment. 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.
create_inline_comment 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 →