Set the description of a merge request
AI agents use set_merge_request_description to create or update resources in GitLab MR MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GitLab MR MCP environment.
This tool modifies merge request data (description) in a reversible manner—the description can be edited or restored later. It does not delete data (Destructive), execute code (Execute), move money (Financial), or merely read data (Read). Setting/updating a merge request description is a Write operation.
From the tool's definition Tool name 'set_merge_request_description' and description 'Set the description of a merge request' indicate modification of an existing merge request's metadata field.
Attacks that exploit this kind of access
Set the description of a merge request. It is categorised as a Write tool in the GitLab MR MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GitLab MR MCP server in PolicyLayer and add a rule for set_merge_request_description: 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 MR MCP. Nothing to install.
set_merge_request_description 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 set_merge_request_description 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 set_merge_request_description. 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.
set_merge_request_description is provided by the GitLab MR MCP server (kevinlin/gitlab-mr-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 →