Create a new discussion on a merge request.
AI agents use create_mr_discussion_tool 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.
This tool creates a new discussion (a comment thread) on a merge request. This is a Write operation because it adds new data to the system reversibly—discussions can be edited or deleted. While it affects collaboration on code review, it does not execute code, delete data irreversibly, or move money.
From the tool's definition Tool description states 'Create a new discussion on a merge request.' The verb 'create' and action of adding a new discussion object represents reversible data modification within GitLab.
Attacks that exploit this kind of access
Create a new discussion on a merge request. 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 create_mr_discussion_tool: 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.
create_mr_discussion_tool 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_mr_discussion_tool 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_mr_discussion_tool. 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_mr_discussion_tool is provided by the MCP Gitlab MCP server (mcp-gitlab-crunchtools). 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 →