About Jira MCP Server
Jira MCP Server lets AI assistants manage Jira issues programmatically through the Jira REST API. It is for teams handling project issues and discussions, with operations spanning creation, lookup, updates, deletion, and comments.
Key features
- 01Create tasks, epics, and subtasks
- 02List issues by status
- 03Update issue summary, description, and status
- 04Retrieve issue details
- 05Delete issues and add comments
Use cases
- 01Create issues in a Jira project
- 02Filter and inspect issue details
- 03Update an issue's status or description
- 04Comment on an existing issue
MCP support
The MCP server exposes Jira REST API operations as tools, including issue management and comments.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEJira MCP Server
A Model Context Protocol server that provides integration with Jira's REST API, allowing AI assistants to manage Jira issues programmatically.
Features
This server provides tools for managing Jira issues:
- Create new issues (Tasks, Epics, Subtasks)
- List issues with optional status filtering
- Update existing issues (summary, description, status)
- Get detailed issue information
- Delete issues
- Add comments to issues
Setup
Prerequisites
- A Jira account with API access
- Jira API token (can be generated from Atlassian Account Settings)
Installation
Installing via Smithery
To install Jira Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install jira-server --client claude
Manual Installation
- Install dependencies:
npm install
- Build the server:
npm run build
Configuration
- Create a
.jira-config.jsonfile in your working directory:
{
"projectKey": ["YOUR_PROJECT_KEY", "YOUR_OTHER_PROJECT_KEY"]
}
- Configure the MCP server with your Jira credentials:
On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"jira": {
"command": "node",
"args": ["/path/to/jira-server/build/index.js"],
"env": {
"JIRA_EMAIL": "[email protected]",
"JIRA_API_TOKEN": "your-api-token",
"JIRA_DOMAIN": "your-domain"
}
}
}
}
Available Tools
create_issue
Creates a new Jira issue
- Required parameters:
- working_dir: Directory containing .jira-config.json
- summary: Issue title
- description: Issue description
- type: Issue type (Task, Epic, or Subtask)
list_issues
Lists issues in the project
- Required parameters:
- working_dir: Directory containing .jira-config.json
- Optional parameters:
- status: Filter by status (e.g., "To Do", "In Progress", "Done")
update_issue
Updates an existing issue
- Required parameters:
- working_dir: Directory containing .jira-config.json
- issue_key: Issue key (e.g., PRJ-123)
- Optional parameters:
- summary: New title
- description: New description
- status: New status
get_issue
Gets detailed information about a specific issue
- Required parameters:
- working_dir: Directory containing .jira-config.json
- issue_key: Issue key (e.g., PRJ-123)
delete_issue
Deletes a Jira issue
- Required parameters:
- working_dir: Directory containing .jira-config.json
- issue_key: Issue key (e.g., PRJ-123)
add_comment
Adds a comment to an existing issue
- Required parameters:
- working_dir: Directory containing .jira-config.json
- issue_key: Issue key (e.g., PRJ-123)
- comment: Comment text to add
Development
For development with auto-rebuild:
npm run watch
Error Handling
The server includes comprehensive error handling for:
- Invalid project keys
- Missing configuration
- Invalid issue types
- API authentication errors
- Invalid status transitions
Output Formatting
Issue information is formatted to include:
- Issue key and summary
- Issue type and status
- Creation date and creator
- Description
- Comments (if any) with author and timestamp
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.