jira-mcp-server
A read-only MCP server that provides AI agents structured access to Jira Cloud, enabling project listing, sprint overview, issue retrieval, and JQL search.
README
Jira MCP Server
A read-only Model Context Protocol (MCP) server that gives AI agents structured access to Jira Cloud.
Features
- Read-only access to Jira Cloud via REST API v3
- Project listing and health summaries
- Epic browsing with progress tracking
- Issue retrieval and JQL search
- Sprint overview with status grouping
- API response caching with configurable TTL
- Tool allowlist/blocklist for fine-grained access control
- Project key restriction to limit query scope
Quick Start
Prerequisites
- Node.js >= 20
- A Jira Cloud instance with an API token (generate one here)
Install and Run
# Install dependencies
npm install
# Copy and fill in environment variables
cp .env.example .env
# Edit .env with your Jira credentials
# Run in development mode
npm run dev
# Or build and run production
npm run build
npm start
Claude Desktop Setup
Add to your claude_desktop_config.json:
{
"mcpServers": {
"jira": {
"command": "node",
"args": ["/absolute/path/to/jira-mcp-server/dist/server.js"],
"env": {
"JIRA_INSTANCE_URL": "https://your-domain.atlassian.net",
"JIRA_API_TOKEN": "your-api-token",
"JIRA_USER_EMAIL": "you@example.com"
}
}
}
}
Claude Code Setup
Add to your project's .mcp.json:
{
"mcpServers": {
"jira": {
"command": "node",
"args": ["/absolute/path/to/jira-mcp-server/dist/server.js"],
"env": {
"JIRA_INSTANCE_URL": "https://your-domain.atlassian.net",
"JIRA_API_TOKEN": "your-api-token",
"JIRA_USER_EMAIL": "you@example.com"
}
}
}
}
Or via the CLI:
claude mcp add jira -- node /absolute/path/to/jira-mcp-server/dist/server.js
Available Tools
| Tool | Description |
|---|---|
list_projects |
List all Jira projects accessible to the server. |
get_project_summary |
Get a high-level project health summary. |
list_epics |
List all epics in a project with progress info. |
get_epic_children |
Get child issues of a specific epic. |
get_issue_subtasks |
Get all subtasks for a given issue. |
get_issue |
Get full details for a specific Jira issue. |
search_issues |
Search Jira issues using JQL. |
get_epic_overview |
Get complete epic overview with all children, descriptions, and subtasks in one call. |
get_active_sprint |
Get the current active sprint with issues grouped by status. |
list_sprints |
List all sprints for a project board (future, active, closed). |
get_issue_comments |
Get comments for a Jira issue with full text content. |
get_issue_transitions |
Get available status transitions for a Jira issue. |
get_issue_changelog |
Get the change history for a Jira issue. |
get_issue_watchers |
Get the list of watchers for a Jira issue. |
list_available_tools |
Returns the list of currently enabled tools. |
clear_cache |
Clears the API response cache. |
Configuration
The server is configured through environment variables (Jira credentials) and an optional JSON config file (tool filters, project restrictions, cache settings).
Set MCP_CONFIG_PATH to point to your config file:
export MCP_CONFIG_PATH=./config.json
See docs/configuration.md for the full configuration reference.
Development
# Run tests
npm test
# Run tests in watch mode
npm run test:watch
# Run tests with coverage
npm run test:coverage
# Lint
npm run lint
# Auto-fix lint issues
npm run lint:fix
# Type-check without emitting
npm run typecheck
# Format code
npm run format
# Validate a config file
npm run validate-config -- --config ./config.json
Docker
Build the image:
docker build -t jira-mcp-server .
Run the container:
docker run --rm \
-e JIRA_INSTANCE_URL="https://your-domain.atlassian.net" \
-e JIRA_API_TOKEN="your-api-token" \
-e JIRA_USER_EMAIL="you@example.com" \
jira-mcp-server
Mount a config file:
docker run --rm \
-e JIRA_INSTANCE_URL="https://your-domain.atlassian.net" \
-e JIRA_API_TOKEN="your-api-token" \
-e JIRA_USER_EMAIL="you@example.com" \
-e MCP_CONFIG_PATH="/app/config/config.json" \
-v ./config.json:/app/config/config.json:ro \
jira-mcp-server
License
MIT
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。