Add a review comment to a pull request
AI agents use add_review_comment to create or update resources in GitLab Review MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GitLab Review MCP environment.
This tool creates new comments on pull requests, which modifies repository state reversibly. While the action is persistent, comments can be edited or deleted, making it a Write operation rather than Destructive.
From the tool's definition Tool description states 'Add a review comment to a pull request', which creates new comment data in the repository system.
Attacks that exploit this kind of access
Add a review comment to a pull request. It is categorised as a Write tool in the GitLab Review MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GitLab Review MCP server in PolicyLayer and add a rule for add_review_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 GitLab Review MCP. Nothing to install.
add_review_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 add_review_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 add_review_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.
add_review_comment is provided by the GitLab Review MCP server (lininn/gitlab-review-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 →