Automate GitLab MR Code Review with n8n: Gemini AI + JIRA Context

Input: GitLab MR comment trigger → Process: extract diff and optional JIRA ticket summary → Output: line-level AI review comments or ALL_CLEAR

Who

Development teams with an n8n instance, GitLab project admin access, and Gemini (plus optional JIRA) credentials

You get

On MR comment trigger, auto-fetch changes and JIRA context, have an LLM review for logic/security/performance issues, and post line-level comments back; post ALL_CLEAR if nothing found

You need

n8n · gitlab · gemini · jira · webhook · http-request

Steps

1. Import template and configure trigger

   Import the workflow JSON from the n8n template library. Open the Webhook node and replace the REPLACE_WITH_UNIQUE_PATH placeholder with a custom path. In your GitLab project settings, configure a webhook to send MR comment events to that URL. Select your LLM credentials in the Gemini (or other LLM) node, and optionally add JIRA credentials. Activate the workflow.

   Setup guidance · Editorial suggestion。Setup assistant starter; confirm prerequisites and permissions

   Copy prompt

   Please help me set up this n8n template:
   1. Import the template JSON (source: https://n8n.io/workflows/7924/)
   2. Configure the Webhook node: replace REPLACE_WITH_UNIQUE_PATH with a unique path
   3. In GitLab project → Settings → Webhooks, add the Webhook URL and select Merge request events or Note events
   4. Configure credentials: select googlePalmApi for the Gemini node; optionally configure jiraSoftwareCloudApi for JIRA nodes
   5. Set the GITLAB_TOKEN environment variable
   6. Activate the workflow, then test by commenting the trigger phrase on an MR
   
   Please confirm each step's inputs and permissions are ready.

2. Trigger listening and data preparation

   When a GitLab MR receives a comment containing the trigger phrase, the Webhook node captures the event. The workflow extracts the project ID and MR IID, storing them in Workflow Static Data for reuse by downstream nodes and error handling. It also posts an "AI review started" status message to the MR. Then it fetches MR changes via the GitLab API, parses the diff into original/new code blocks; if the MR description contains a JIRA issue key, it fetches the issue summary, and for subtasks also fetches the parent issue summary, merging both into context.

3. LLM code review

   The parsed diff blocks and optional JIRA context are fed into the Basic LLM Chain. Gemini 2.5 Pro follows system instructions to focus only on logic correctness, security, and performance issues, ignoring style and filenames. When issues are found, it outputs actionable suggestions prefixed with 🤖 **AI Review:**; when none are found, it returns ALL_CLEAR.

   Execution prompt · Source text。Basic LLM Chain node messages.messageValues[0].message field (System Message)

   Copy prompt

   You are an automated code review bot. Your primary goal is to identify high-value issues in code.
   
   **Instructions:**
   
   1. **Analysis Focus:** Concentrate only on business logic, correctness, security, and performance. Ignore style, naming, filenames, version bumps, and non-source files. Assume placeholders for yml files will be filled with correct values.
   2. **Output for Issues:** When you find an issue, begin your response with the prefix `🤖 **AI Review:** `. Follow it with a concise, actionable explanation. Prefer one-liners that are immediately actionable - what or where or why and how to fix.
   3. **Output for No Issues:** If your analysis finds **zero** issues worth reporting, your **ENTIRE** response must be the single keyword: `ALL_CLEAR`. Do not add any other text or explanation.
   4. ** Findings to ignore in yaml files:**
       - Ignore if a value for vaultSecretPath in a values file or a yaml contains a double slash (//)
       - Ignore errors where tag appears to be very or too specific
   
   **Important Rules:**
   
   * NEVER write praise, summaries, or conversational phrases like "I have no findings."
   * If you find issues, start every comment with the `🤖 **AI Review:** ` prefix.
   * If you find no issues, don't output anything.

   Execution prompt · Source text。Basic LLM Chain node text field (User Message / Prompt)

   Copy prompt

   =First, consider the context from the associated JIRA ticket:
   ------------
   {{ $json.jiraParentContext || $json.jiraContext || 'No JIRA context was provided.' }}
   ------------
   
   File path：{{ $('Skip File Changes').item.json.new_path }}
   
   ```Original code
    {{ $json.originalCode }}
   ```
   change to
   ```New code
    {{ $json.newCode }}
   ```
   Please review the code changes in this section:

   Execution prompt · Source text。Confirm the destination, input variables and output format before use.

   Copy prompt

   ### ⭐️ Try It Out!
   
   Welcome! This template adds AI-powered code reviews to your GitLab Merge Requests. Simply comment **`ai-review`** on any MR and watch the workflow:
   
   - Captures the comment event.
   - Fetches diff & optional JIRA context.
   - Asks an LLM for insights.
   - Posts inline comments or an 'all clear' note.
   
   Perfect for catching logic, security and performance issues fast.

   Execution prompt · Source text。Confirm the destination, input variables and output format before use.

   Copy prompt

   ### 🟢 Step 1: Listen & Capture
   
   A Webhook node listens for merge request note events. When the comment text matches your trigger (default: `ai-review`), it:
   
   - Extracts the Project & MR IDs and stores them in a **Static Context** (see below) so later nodes always know where to post results.
   - Posts a short "AI review started" message back to the MR to let reviewers know the bot is working.

   Execution prompt · Source text。Confirm the destination, input variables and output format before use.

   Copy prompt

   ### 🟣 Step 2: Prepare & Review
   
   The workflow fetches the merge request changes via the GitLab API and parses the diff into original vs new code blocks.
   
   If the MR description contains a Jira key, the workflow fetches the issue summary and, if it's a subtask, also fetches the parent ticket for extra context. Both summaries are combined into the prompt.
   
   An LLM (Gemini by default) is prompted to find critical issues only—logic bugs, security flaws and performance problems—and to return comments with file and line numbers. If no issues exist, the model returns `ALL_CLEAR`.

   Execution prompt · Source text。Confirm the destination, input variables and output format before use.

   Copy prompt

   ### 🟠 Step 3: Post & Fallback
   
   Review comments are converted into GitLab discussion payloads and posted back to the MR at the correct file and line positions.
   
   If a comment’s position is not calculated properly, the workflow falls back to posting a comment as a thread at the MR level so nothing is lost.

   Execution prompt · Source text。Confirm the destination, input variables and output format before use.

   Copy prompt

   ### 🔵 Static Context & Error Handling
   
   Workflow Static Data is used to store persistent values—like the project ID and the MR ID so that they will be available across branches.
   
   This is critical for the Error Trigger: if something fails, the error path can still post to the correct MR using these stored IDs. Without static context, error comments wouldn’t know where to go.

   Execution prompt · Source text。Confirm the destination, input variables and output format before use.

   Copy prompt

   ### 🟡 Need Help & Customise
   
   - Change the trigger word in the **IF** node to match your own.
   - Swap in your preferred LLM or adjust the prompt to suit your guidelines.
   - Filter by file type or exclude certain directories in the parsing logic.

4. Post results and error fallback

   After LLM outputs are aggregated, the Process Comments node filters for valid review comments. If issues exist, they are converted to GitLab discussion payloads and posted at line-level positions; if position calculation fails, the workflow falls back to posting as an MR-level thread. If all outputs are ALL_CLEAR, a "No significant issues were found. LGTM!" note is posted. The Error Trigger path uses the project ID and MR ID stored in Static Data to send an error notification to the correct MR, then cleans up Static Data.

5. Customize and tune

   You can change the trigger phrase in the IF node (Need Review), adjust the system message in the Basic LLM Chain to focus on style or documentation, add file-type filters in the Skip File Changes or Prepare Code Changes nodes, or integrate Slack/Email nodes to send completion notifications.

Please help me set up this n8n template:
1. Import the template JSON (source: https://n8n.io/workflows/7924/)
2. Configure the Webhook node: replace REPLACE_WITH_UNIQUE_PATH with a unique path
3. In GitLab project → Settings → Webhooks, add the Webhook URL and select Merge request events or Note events
4. Configure credentials: select googlePalmApi for the Gemini node; optionally configure jiraSoftwareCloudApi for JIRA nodes
5. Set the GITLAB_TOKEN environment variable
6. Activate the workflow, then test by commenting the trigger phrase on an MR

Please confirm each step's inputs and permissions are ready.