fetch_merge_request_diff
AI agents call fetch_merge_request_diff to retrieve information from GitLab Code Review MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries merge request diff data without side effects. It supports read-only code analysis workflows. The empty description reduces confidence slightly, but the tool name and server context clearly indicate a data retrieval operation with no ability to modify, delete, or execute code.
From the tool's definition Tool name 'fetch_merge_request_diff' indicates retrieval of diff data. Server description states the tool enables 'fetching diffs' and 'analyzing code changes' as part of code review workflows.
Attacks that exploit this kind of access
fetch_merge_request_diff. It is categorised as a Read tool in the GitLab Code Review MCP MCP Server, which means it retrieves data without modifying state.
Register the GitLab Code Review MCP server in PolicyLayer and add a rule for fetch_merge_request_diff: 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 Code Review MCP. Nothing to install.
fetch_merge_request_diff 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 fetch_merge_request_diff 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 fetch_merge_request_diff. 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.
fetch_merge_request_diff is provided by the GitLab Code Review MCP server (lininn/gitlab-code-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 →