jira-mcp

JIRA MCP Server

An MCP server that enables Large Language Models (LLMs) to interact with JIRA through standardized tools and context. This server provides capabilities for searching issues using JQL and retrieving detailed issue information.

Features

• JQL Search: Execute complex JQL queries with pagination support
• Issue Details: Retrieve detailed information about specific JIRA issues

Prerequisites

• npm installed
• A JIRA instance with API access
• JIRA API token or Personal Access Token
• JIRA user email associated with the API token

Getting JIRA API Credentials

• Log in to your Atlassian account at https://id.atlassian.com
• Navigate to Security settings
• Under API tokens, select "Create API token"
• Give your token a meaningful name (e.g., "MCP Server")
• Copy the generated token - you won't be able to see it again!
• Use this token as your JIRA_API_KEY
• Use the email address associated with your Atlassian account as JIRA_USER_EMAIL

Usage

Integration with Claude Desktop

• Add the server configuration to Claude Desktop's config file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "jira": {
      "command": "npx",
      "args": ["-y", "jira-mcp"],
      "env": {
        "JIRA_INSTANCE_URL": "https://your-instance.atlassian.net",
        "JIRA_USER_EMAIL": "[e-mail]",
        "JIRA_API_KEY": "your-api-token"
      }
    }
  }
}

• Restart Claude Desktop to load the new configuration.

Available Tools

1. JQL Search (jql_search)

Executes a JQL search query with customizable parameters.

Parameters:

• jql (required): JQL query string
• nextPageToken: Token for pagination
• maxResults: Maximum number of results to return
• fields: Array of field names to include
• expand: Additional information to include

Example:

{
  "jql": "project = 'MyProject' AND status = 'In Progress'",
  "maxResults": 10,
  "fields": ["summary", "status", "assignee"]
}

2. Get Issue (get_issue)

Retrieves detailed information about a specific issue.

Parameters:

• issueIdOrKey (required): Issue ID or key
• fields: Array of field names to include
• expand: Additional information to include
• properties: Array of properties to include
• failFast: Whether to fail quickly on errors

Example:

{
  "issueIdOrKey": "PROJ-123",
  "fields": ["summary", "description", "status"],
  "expand": "renderedFields,names"
}

Development

Configuration

Set up your environment variables before running the server. Create a .env file in the root directory:

JIRA_INSTANCE_URL=https://your-instance.atlassian.net
JIRA_USER_EMAIL=[e-mail]
JIRA_API_KEY=your-api-token

Replace the values with:

• Your actual JIRA instance URL
• The email address associated with your JIRA account
• Your JIRA API token (can be generated in Atlassian Account Settings)

Installation

Installing via Smithery

To install JIRA for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install jira-mcp --client claude

Manual Installation

• Clone this repository:

git clone <repository-url>
cd jira-mcp

• Install dependencies:

npm install

Running with MCP Inspector

For testing and development, you can use the MCP Inspector:

npm run inspect

Adding New Tools

To add new tools, modify the ListToolsRequestSchema handler in index.js:

server.setRequestHandler(ListToolsRequestSchema, async () => {
  return {
    tools: [
      // Existing tools...
      {
        name: "your_new_tool",
        description: "Description of your new tool",
        inputSchema: {
          // Define input schema...
        }
      }
    ]
  };
});

Then implement the tool in the CallToolRequestSchema handler.

License

MIT

Contributing

Contributions are welcome! Please feel free to submit a PR.