JIRA

You can run a MCP server that interfaces with JIRA to retrieve, search, and create issues, plus access project and user information. This MCP makes it easy for AI-based assistants to work with JIRA data through straightforward commands and reliable runtime behavior.

How to use

You will run the MCP server locally and connect an MCP client to it. Once running, you can issue natural language requests that map to JIRA actions, such as getting details for a specific issue, creating a new issue with a summary and description, or searching for issues using JQL. You can also request project information or current user details to tailor responses to your JIRA workspace.

How to install

Prerequisites you need before installing this MCP server are clearly defined so you can prepare your environment.

Install prerequisites and set up the project locally with these steps.

# Prerequisites
# Ensure you have Python 3.13 or higher installed on your system

# Step 1: Clone the MCP project repository
git clone <repository-url>
cd longcon-mcp-demo

# Step 2: Install dependencies
# Using uv (recommended)
uv sync

# Or using pip
pip install -r requirements.txt

Configuration

Configure JIRA access and start the server by setting up the JIRA credentials and pointing the server at your JIRA instance.

# 1. JIRA Setup
# Create a JIRA Personal Access Token (PAT)
# 2. Create a .env file in the project root with:
JIRA_USERNAME=your-email@example.com
JIRA_PAT=your-personal-access-token
JIRA_URL=https://your-instance.atlassian.net

# 3. Update project keys inside jira_project_keys() to include your keys
# def jira_project_keys():
#     return ['YOUR_PROJECT_KEY']

# 4. Run the server locally to verify it starts
python main.py

The server should start without errors. Press Ctrl+C to stop it.

## Additional configuration notes

Claude Desktop configuration provides ready-to-use options for connecting to the MCP server. You can run the server directly with Python or through uv as shown in the examples. If you prefer using environment variables instead of the .env file, set JIRA\_USERNAME and JIRA\_PAT accordingly in the MCA client configuration.

## Security and maintenance notes

- Never expose your JIRA PAT or credentials. Store them securely and rotate tokens periodically.
- Restrict PAT permissions to only what is needed for MCP interactions.
- Keep dependencies up to date and monitor for updates to the MCP runtime to mitigate known vulnerabilities.

## Troubleshooting

If you encounter issues, verify that your JIRA\_USERNAME, JIRA\_PAT, and JIRA\_URL are correctly set and that the server process is running. If the server cannot connect to JIRA, double-check network access and the PAT scope. Ensure the absolute path you supply for the main script matches your local environment when configuring the MCP client.

## Verification

To verify, start a new conversation with your MCP client and ask for JIRA-related data. For example, request details of a known issue or ask the client to search for issues with specific criteria. The MCP will fetch data from JIRA and present it through the client interface.

## Available tools

### get\_jira\_issue

Fetch detailed information for a specific JIRA issue by key and present fields such as status, assignee, and description.

### create\_jira\_issue

Create a new JIRA issue with a provided project, issue type, summary, and description, returning the created issue key.

### search\_jira\_issues

Search for JIRA issues using JQL criteria and return a list of matching issues with key metadata.

### get\_project\_keys

Retrieve available JIRA project keys to help users scope their queries and issue creation.

### get\_current\_user

Return information about the current authenticated JIRA user.