Jira MCP Server
Enables comprehensive interaction with self-hosted Jira instances using Personal Access Token authentication, supporting issue management, JQL searches, comments, transitions, projects, and custom fields through 27 specialized tools.
README
Jira MCP Server
<!-- Add these badges once published to GitHub/npm -->
<!-- -->
<!--
-->
<!--
-->
<!--
-->
<!--
-->
<!--
-->
A Model Context Protocol (MCP) server for self-hosted Jira instances using Personal Access Token (PAT) authentication.
✨ Features
- Issue Management: Get, create, update, delete, and assign issues
- Search: Search issues using JQL
- Comments: Get, add, update, and delete comments
- Transitions: Get available transitions and transition issues
- Projects: List and get project details
- Users: Search users and get current user
- Watchers: Add watchers to issues
- Issue Links: Link issues together
📋 Prerequisites
- Node.js 18+
- Self-hosted Jira instance (tested with v9.12.12)
- Personal Access Token (PAT) for authentication
🚀 Installation
npm install
npm run build
⚙️ Configuration
Create a .env file in the project root:
JIRA_BASE_URL=https://your-jira-instance.com/
PAT=your-personal-access-token
Getting a Personal Access Token
- Log in to your Jira instance
- Go to Profile → Personal Access Tokens
- Create a new token with appropriate permissions
- Copy the token to your
.envfile
📖 Usage
Running the Server
npm start
Development Mode
npm run dev
Using with npx (Recommended)
No installation required! Add the following to your MCP configuration:
{
"mcpServers": {
"jira": {
"command": "npx",
"args": ["-y", "jira-mcp-server-pro"],
"env": {
"JIRA_BASE_URL": "https://your-jira-instance.com/",
"PAT": "your-personal-access-token"
}
}
}
}
Global Installation
npm install -g jira-mcp-server-pro
Then add to your MCP configuration:
{
"mcpServers": {
"jira": {
"command": "jira-mcp-server-pro",
"env": {
"JIRA_BASE_URL": "https://your-jira-instance.com/",
"PAT": "your-personal-access-token"
}
}
}
}
Local Development
If running from source, add the following to your MCP configuration:
{
"mcpServers": {
"jira": {
"command": "node",
"args": ["/path/to/jiraMCP/dist/index.js"],
"env": {
"JIRA_BASE_URL": "https://your-jira-instance.com/",
"PAT": "your-personal-access-token"
}
}
}
}
🛠️ Available Tools (27 total)
Issue Operations
| Tool | Description |
|---|---|
jira_get_issue |
Get details of a Jira issue by its key |
jira_search_issues |
Search for issues using JQL |
jira_create_issue |
Create a new issue (basic fields) |
jira_create_issue_advanced |
Create issue with full field support (fixVersions, components, custom fields) |
jira_update_issue |
Update an existing issue (basic fields) |
jira_update_issue_advanced |
Update issue with full field support |
jira_delete_issue |
Delete an issue |
jira_assign_issue |
Assign or unassign an issue |
jira_get_transitions |
Get available transitions for an issue |
jira_transition_issue |
Transition an issue to a new status |
jira_link_issues |
Link two issues |
jira_add_watcher |
Add a watcher to an issue |
Comments
| Tool | Description |
|---|---|
jira_get_comments |
Get comments on an issue |
jira_add_comment |
Add a comment to an issue |
Projects
| Tool | Description |
|---|---|
jira_get_projects |
Get all projects |
jira_get_project |
Get details of a specific project |
jira_get_project_versions |
Get all versions for a project (for fixVersions) |
jira_get_project_components |
Get all components for a project |
Metadata & Field Discovery
| Tool | Description |
|---|---|
jira_get_create_meta |
IMPORTANT: Get required fields and allowed values for creating issues |
jira_get_edit_meta |
Get editable fields and allowed values for an existing issue |
jira_get_fields |
Get all available fields including custom fields |
jira_get_field_options |
Get allowed values for a specific field |
jira_get_priorities |
Get all available priorities |
jira_get_statuses |
Get all available statuses |
jira_get_issue_link_types |
Get all available issue link types |
Users
| Tool | Description |
|---|---|
jira_search_users |
Search for users |
jira_get_current_user |
Get the current authenticated user |
📝 Workflow: Creating Issues with Required Fields
-
First, call
jira_get_create_metato discover required fields and allowed values:jira_get_create_meta(projectKey: "PROJ", issueType: "Bug")This returns all fields with their requirements and dropdown options.
-
Then, use
jira_create_issue_advancedwith the correct values:jira_create_issue_advanced( projectKey: "PROJ", summary: "Issue title", issueType: "Bug", fixVersions: ["1.0.0"], components: ["Backend"], customFields: {"customfield_10001": "value"} )
📚 Resources
The server exposes MCP Resources for quick access to Jira data without tool calls:
| Resource URI | Description |
|---|---|
jira://config |
Server configuration and connection info |
jira://current-user |
Currently authenticated user details |
jira://priorities |
All available issue priorities |
jira://statuses |
All available issue statuses |
jira://fields |
All fields (system + custom) grouped by type |
jira://link-types |
Available issue link types |
jira://projects |
List of all projects (key, name, type) |
jira://project/{KEY} |
Project details with versions, components, issue types |
jira://my-issues |
Issues assigned to current user |
Using Resources
Resources provide context without explicit tool calls. For example, reading jira://project/MSSP returns:
{
"key": "MSSP",
"name": "MSSP",
"versions": [{"name": "1.0.0", "released": true}, ...],
"components": [{"name": "LOGIN"}, {"name": "MSSP-FO"}, ...],
"issueTypes": [{"id": "1", "name": "Bug"}, {"id": "3", "name": "Task"}, ...]
}
🔍 Example JQL Queries
# Issues assigned to me
assignee = currentUser()
# Open bugs in a project
project = PROJ AND issuetype = Bug AND status != Done
# Issues created in the last 7 days
created >= -7d
# High priority issues
priority in (Highest, High)
🤝 Contributing
Contributions are welcome! Here's how you can help:
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
Development Setup
# Clone your fork
git clone https://github.com/YOUR_USERNAME/jira-mcp-server.git
cd jira-mcp-server
# Install dependencies
npm install
# Run in development mode
npm run dev
Reporting Issues
- Use the GitHub Issues to report bugs
- Include your Node.js version, Jira version, and steps to reproduce
- Check existing issues before creating a new one
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
🙏 Acknowledgments
- Model Context Protocol for the MCP specification
- Atlassian for Jira REST API documentation
<p align="center"> Made with ❤️ for the MCP community </p>
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。