Get general and file diff comments of a certain merge request
AI agents call get_merge_request_comments to retrieve information from GitLab MR MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves comments from a merge request without creating, modifying, or deleting any data. It performs a read-only query operation with no side effects. The blast radius if misused is minimal — an agent could retrieve comments it shouldn't have visibility of, but cannot alter or destroy anything. Classification: Read.
From the tool's definition Tool name is 'get_merge_request_comments' and description states 'Get general and file diff comments' — indicates retrieval of existing data with no modification capability.
Attacks that exploit this kind of access
Get general and file diff comments of a certain merge request. It is categorised as a Read tool in the GitLab MR MCP MCP Server, which means it retrieves data without modifying state.
Register the GitLab MR MCP server in PolicyLayer and add a rule for get_merge_request_comments: 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.
get_merge_request_comments is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_merge_request_comments 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 get_merge_request_comments. 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.
get_merge_request_comments 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 →