GitLab MR Automated Code Review & AI Risk Assessment

GitLab merge request trigger → extract code diff → Claude/GPT risk analysis → structured report → email & MR comment notification

Who

DevOps and engineering teams using n8n who want to automate merge request review

You get

When an MR is created or updated, automatically fetch code changes, have AI assess risk level, identify issues, provide fix recommendations and test cases, then notify dev and QA teams via email and GitLab MR comment

You need

n8n · http-request · code · ai-agent · structured-output · anthropic · gmail

Steps

1. Configure GitLab Trigger

   Add a GitLab Trigger node in n8n, connect GitLab API credentials, select the merge_requests event, and specify the repository (owner/repository) to monitor. After saving, n8n will auto-generate and register the webhook.

2. Extract MR Code Diff

   Add an HTTP Request node (Extract Diff) configured to call the GitLab API: GET /api/v4/projects/{project}/merge_requests/{iid}/changes. Use expressions to dynamically pull the project path and MR IID from trigger data, and provide the GitLab API Token in the Header.

3. Verify Changes Are Non-Empty

   Add an If node (If Some Change) that checks whether the changes array length from the diff response is greater than 0. If empty, terminate the workflow to avoid analyzing no-op MRs.

4. AI Analysis & Structured Output

   Configure the AI Agent node, connecting an Anthropic Chat Model (or alternative). The node uses define mode with a complete tool schema requiring the AI to return JSON: RiskLevel, Summary, Recommendations, Issues, URL, DiffTable, TestCases. Pass the diff content and MR URL as user messages. Downstream, connect Auto-fixing Output Parser and Structured Output Parser to enforce output format compliance.

   Execution prompt · Source text。n8n AI Agent node Parameters > Text (define mode), as the complete tool-calling configuration and message content

   Copy prompt

   ={
     "model": "claude-3-5-haiku-20241022",
     "max_tokens": 1000,
     "temperature": 0.7,
     "tools": [
       {
         "name": "record_summary",
         "description": "Record a structured summary of a git diff using well-defined JSON.",
         "input_schema": {
           "type": "object",
           "properties": {
             "RiskLevel": {
               "type": "string",
               "description": "Overall risk assessment of the changes: High/Medium/Low."
             },
             "Summary": {
               "type": "string",
               "description": "One-line summary of the git diff analysis"
             },
             "Recommendations": {
               "type": "array",
               "items": {
                 "type": "object",
                 "properties": {
                   "Recommendation": {
                     "type": "string",
                     "description": "Specific recommendation in HTML format."
                   },
                   "CodeSnippet": {
                     "type": "string",
                     "description": "Relevant code full snippet formatted in HTML."
                   }
                 },
                 "required": ["Recommendation", "CodeSnippet"]
               }
             },
             "Issues": {
               "type": "array",
               "items": {
                 "type": "object",
                 "properties": {
                   "File": {
                     "type": "string",
                     "description": "HTML-formatted name of the file where the issue exists."
                   },
                   "PotentialIssue": {
                     "type": "string",
                     "description": "HTML-formatted description of the issue."
                   },
                   "Severity": {
                     "type": "string",
                     "description": "Severity of the issue: High/Medium/Low in HTML."
                   }
                 },
                 "required": ["File", "PotentialIssue", "Severity"]
               }
             },
             "URL": {
               "type": "string",
               "description": "Link to the repository in HTML."
             },
             "DiffTable": {
               "type": "object",
               "properties": {
                 "FileName": {
                   "type": "string",
                   "description": "HTML-formatted name of the file."
                 },
                 "Changes": {
                   "type": "array",
                   "items": {
                     "type": "object",
                     "properties": {
                       "Line": {
                         "type": "string",
                         "description": "HTML-formatted line number."
                       },
                       "Before": {
                         "type": "string",
                         "description": "Code before the change formatted in HTML."
                       },
                       "After": {
                         "type": "string",
                         "description": "Code after the change formatted in HTML."
                       }
                     },
                     "required": ["Line", "Before", "After"]
                   }
                 }
               }
             },
             "TestCases": {
               "type": "array",
               "description": "List of test cases the QA team must check.",
               "items": {
                 "type": "object",
                 "properties": {
                   "TestFor": {
                     "type": "string",
                     "description": "Description of the functionality or area to test."
                   },
                   "Steps": {
                     "type": "string",
                     "description": "HTML-formatted steps to test the functionality."
                   },
                   "ExpectedOutcome": {
                     "type": "string",
                     "description": "HTML-formatted description of the expected result of the test."
                   }
                 },
                 "required": ["TestFor", "Steps", "ExpectedOutcome"]
               }
             }
           },
           "required": ["RiskLevel", "Summary", "Recommendations", "Issues", "URL", "DiffTable", "TestCases"]
         }
       }
     ],
     "tool_choice": {
       "type": "tool",
       "name": "record_summary"
     },
     "messages": [
       {
         "role": "user",
         "content": [
           {
             "type": "text",
             "text": "Analyze the following git diff, highlight potential issues, provide recommendations with code snippets (using HTML formatting for all values), and include the URL. Ensure proper risk evaluation. Mark issues that may break the build or reveal a security risk as High':"
           },
           {
             "type": "text",
             "text": "{{ $json.changes.map(change => JSON.stringify(change.diff).slice(1, -1).replace(/[\r]/g, '')).join(' ') }}"
           },
           {
             "type": "text",
             "text": "URL: {{ $json.web_url }}"
           },
           {
             "type": "text",
             "text": "Provide a table of test cases for the QA team under the 'TestCases' field."
           }
         ]
       }
     ]
   }

5. Generate Notification List

   Add a Code node (Distribution List Generator) that uses JavaScript to map project names to dev/qa email lists, merges with a global list and the committer email, deduplicates, and outputs a comma-separated string. You must replace the example project names and placeholder emails with actual team configuration.

6. Send Email & MR Comment

   Configure two nodes in parallel: 1) Gmail node (Send to DL) receiving the emails output from Distribution List Generator, sending an HTML-formatted report email with subject containing risk level and project name; 2) HTTP Request node (Comment Back on MR) POSTing to the GitLab MR notes API, rendering AI output as Markdown table comments. Both require replacing credentials and project path expressions.

This is an official n8n template. After importing, check in this order:
1. Replace the owner/repository in GitLab Trigger with your actual repository;
2. Enter a valid GitLab API Token in the Headers of Extract Diff and Comment Back on MR (not placeholders);
3. Configure Anthropic API credentials (or switch to OpenAI);
4. Replace the project-to-email mapping in Distribution List Generator with actual team addresses;
5. Configure Gmail OAuth2 credentials and update email subject variables;
6. Create a test MR to verify triggering, analysis, email delivery, and comment posting.