Personal Jira

You have a dedicated MCP server that lets an AI assistant connect to JIRA to query issues, manage projects and attachments, and perform common JIRA actions through a standardized MCP interface.

How to use

Start the MCP server in stdio mode to enable direct communication with your MCP client. You can run it from the command line and then point your MCP client at the standard input/output interface to perform actions like querying issues, creating or updating issues, and downloading attachments.

How to install

Prerequisites you need on your machine before installing this MCP server include Python 3.10 or higher and a simple package manager setup.

# Optional: install uv for quick package management (recommended)
curl -sSf https://astral.sh/uv/install.sh | sh
# or use pip to install uv if you prefer
pip install uv

# Verify installation
uv --version

Additional configuration and usage notes

Configure environment variables for the JIRA connection in a .env file before starting the server.

JIRA_SERVER_URL=http://your-jira-instance.com
JIRA_USERNAME=your_username
JIRA_PASSWORD=your_password
# Or use an API token instead of a password
JIRA_API_TOKEN=your_api_token

Running the MCP server

You have two complete stdio-based start configurations you can use. Pick one that fits your tooling, then run it in a shell to start listening on standard input/output.

{
  "mcpServers": {
    "personal-jira_mcp": {
      "command": "uvx",
      "args": [
        "--from=personal-jira-mcp",
        "personal-jira-mcp",
        "--transport",
        "stdio"
      ],
      "env": {
        "JIRA_SERVER_URL": "http://your-jira-instance.com",
        "JIRA_USERNAME": "your_username",
        "JIRA_PASSWORD": "your_password"
      }
    }
  }
}

(source for the above option)

## Cursor/CLI-compatible start (alternative)

If you already installed the MCP server locally, you can start it directly with the following configuration.

{ "mcpServers": { "personal-jira_mcp": { "command": "personal-jira-mcp", "args": ["--transport", "stdio"], "env": { "JIRA_SERVER_URL": "http://your-jira-instance.com", "JIRA_USERNAME": "your_username", "JIRA_PASSWORD": "your_password" } } } }

## Using the MCP server with a client

Once the server is running, configure your MCP client to connect via stdio. You can specify the same environment variables used to start the server and begin issuing commands to get issue details, list issues, create or update issues, and manage attachments.

## Troubleshooting and tips

- Ensure the JIRA server URL is reachable from the machine running the MCP server.
- If authentication fails, verify that your username and password or API token are correct and have appropriate permissions in JIRA.
- Confirm the MCP server process is running and that the client is connected via stdio as expected.

## Security considerations

Keep credentials in a secure location, prefer API tokens over passwords when supported, and restrict access to the MCP channel to trusted clients.

## Available tools

### get\_issue

Fetch details for a specific Jira issue by its key (e.g., ERP-161)

### search\_issues

Search and list Jira issues using a JQL query (e.g., project = ERP AND status = "In Progress")

### create\_issue

Create a new Jira issue with a given title and description

### update\_issue

Update fields of an existing Jira issue identified by its key

### get\_projects

Retrieve a list of Jira projects accessible to the user

### get\_project

Get detailed information about a specific Jira project

### get\_issue\_attachments

List all attachments for a Jira issue

### download\_all\_attachments

Download all attachments for a Jira issue

### get\_attachment\_by\_filename

Retrieve a specific attachment by filename from a Jira issue