GeminiWorkPlanningAI score · 74/100AI-assisted edit · no obvious prompt-injection riskn8n.io

Natural-Language Chat-Driven Jira Issue Management: n8n + Gemini + MCP

Send chat messages to n8n, let Gemini interpret intent, and execute Jira operations via an MCP server

ExperiencedStepsWorkflowPromptTip
Who
Developers or project managers who frequently create or query Jira issues and want to replace manual form-filling with natural language
You get
Send natural-language commands in a chat window to auto-create Jira issues with descriptions and acceptance criteria, check status, and add comments
You need
n8n · Jira

Constraints

Prerequisites: n8n instance (cloud or self-hosted), Jira Software account with API token, Google Gemini API credentials, a configured and accessible MCP server. Basic n8n workflow experience recommended.

What they did

Author rohitdabra built a 20-node n8n workflow template: 'When Chat Message Received' triggers messages into an 'AI Agent' node; the Agent calls 'Google Gemini Chat Model' as the LLM, 'Simple Memory' for context, 'MCP Client' to connect to an MCP server, and 13 Jira tool nodes (exposed via MCP Server Trigger) for CRUD operations on issues and comments.

How it went

Author reports (author_report): sending a chat message like 'Can you create an issue in Jira for Login Page with detailed description and acceptance criteria?' auto-creates a Jira issue with structured description and acceptance criteria; 'What's the status of issue PROJ-123?' returns current status; comment commands add comments to specified issues.

Worth knowing

The MCP server must be pre-deployed and reachable; the MCP Client endpointUrl in workflow.json defaults to localhost and must be replaced with your actual MCP server address. The template does not include explicit error-handling or retry nodes—add these for production. Adjust Simple Memory retention to avoid unbounded growth. This site has not executed the template; reproduction status is not_tested.

Steps

  1. Import the workflow

    Copy the workflow JSON from the n8n template page, open your n8n instance, click Import > From Text, paste the JSON, and click Import. After importing, you should see a canvas with 20 nodes.

  2. Configure Google Gemini

    Open the Google Gemini Chat Model node and add your Google Gemini API credentials. Suggested parameters: Model = gemini-pro; Temperature = 0.7; Max tokens = as needed.

  3. Set up MCP server connection

    Open the MCP Client node and enter your MCP server endpoint URL (e.g., http://localhost:5678/mcp/837401df-ddca-4f2c-b71d-34724355b21e), add required authentication credentials, and set timeout values. Ensure the MCP server supports Jira operations: issue creation/retrieval, comment management, status updates, and changelog access.

  4. Configure Jira integration

    In n8n, go to Credentials > Add Credential, select Jira Software API, and enter your Jira instance URL, email, and API token. Then configure each Jira tool node: Get Issue Status — set project key and filters; Create Issue — define issue type and required fields (template defaults: project 10000, issue type 10003 Story); Manage Comments — set permissions and content rules.

  5. Configure memory

    Open the Simple Memory node, set a memory key for conversation context, define memory retention duration, and configure memory scope (user or session level).

  6. Set up chat trigger

    Configure the When Chat Message Received trigger: set up the webhook URL or chat platform integration, define message filters if needed, and test with sample messages. Activate the workflow when ready.

    Execution prompt · Source text。Send it in the n8n chat window (Chat Trigger)

    Add a comment to issue PROJ-123: "Ready for testing in staging environment"

  7. Safety tip: human confirmation before action

    Safety tip (editorial safety note, not the template author's practice): before the agent actually creates, updates or deletes Jira issues or sends notifications, have a human confirm each change.

Prompt you can copy

Execution prompt · Source text。Send it in the n8n chat window (Chat Trigger)

This block is the prompt. Ads are never placed here.

Can you create an issue in Jira for Login Page with detailed description and acceptance criteria?

This prompt is for setup/reproduction guidance, not a node runtime instruction. Fill node parameters using the template description and actual values from workflow.json.

Source

Jira project management automation with Google Gemini & MCP server · rohitdabra · n8n.io · 2025-09-22T16:26:50.376Z

Comments & feedback

Tried this method? Share results, problems or improvements. Comments appear after moderation. Please avoid sensitive information.

Loading…

    Related