Jira MCP Server
Enables creating, fetching, and updating Jira issues via the REST API with support for ADF descriptions and common fields like priority, labels, and issue types.
README
Jira MCP Server
An MCP (Model Context Protocol) server for creating and fetching Jira issues via the REST API. Built with Bun.
Features
- Fetch and update existing Jira issues
- Create Jira issues with a single tool call
- Support for all standard issue fields (summary, description, type, priority, labels)
- Flexible description input:
- Plain text → automatic conversion to basic ADF paragraphs
- Pre-formatted ADF objects → full control over formatting (panels, headings, lists, etc.)
- Runtime ADF validation with Zod schemas
- Standalone executable (no runtime dependencies)
--helpflag for quick setup reference
Prerequisites
- Bun v1.0+ — install with
curl -fsSL https://bun.sh/install | bash- Or use devbox for an isolated environment without a permanent Bun installation (see below)
- A Jira Cloud instance
- Jira API token (see Atlassian API tokens)
Installation
git clone <your-repo-url>
cd jira-mcp-server
bun install
Using devbox (no permanent Bun installation)
If you prefer not to install Bun globally, devbox provides an isolated shell with Bun available:
# Install devbox (one-time)
curl -fsSL https://get.jetify.com/devbox | bash
# Enter the devbox shell (installs Bun automatically)
devbox shell
# Now use bun as normal
bun install
bun run build
Run exit to leave the devbox shell. Bun is not added to your system outside of it.
Configuration
The server requires these environment variables:
| Variable | Description | Example |
|---|---|---|
JIRA_URL |
Your Jira instance URL | https://your-domain.atlassian.net |
JIRA_EMAIL |
Your Jira account email | user@example.com |
JIRA_API_TOKEN |
Your Jira API token | your-api-token |
JIRA_PROJECT |
Default project key for issue creation | PROJ |
Usage
# Build standalone executable
bun run build
# Build and deploy to ~/bin
bun run deploy
# Build, deploy, and sign (required on macOS — see note below)
bun run deploy-and-sign
# Run from source (development)
bun run dev
# Inspect with MCP Inspector
bun run mcp-inspect
# Display setup instructions
./dist/jira-mcp-server --help
macOS: use deploy-and-sign
On macOS, use bun run deploy-and-sign instead of bun run deploy. When bun build --compile produces a binary, it embeds a code signature. Copying the file with cp invalidates that signature because macOS recalculates file hashes on copy. Gatekeeper then kills the binary with SIGKILL when you try to run it from the new location.
deploy-and-sign adds an ad-hoc re-signing step (codesign -s -) after the copy, which satisfies macOS without requiring an Apple Developer certificate.
Integration with MCP Clients
Claude Desktop
Add to your config file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"jira": {
"command": "/absolute/path/to/jira-mcp-server/dist/jira-mcp-server",
"env": {
"JIRA_URL": "https://your-domain.atlassian.net",
"JIRA_EMAIL": "user@example.com",
"JIRA_API_TOKEN": "your-token",
"JIRA_PROJECT": "PROJ"
}
}
}
}
For development (running from source), replace command with "bun" and add "args": ["run", "/absolute/path/to/jira-mcp-server/src/index.ts"].
Cursor
- Open Cursor Settings → Features → MCP
- Add a new MCP server:
- Transport type: stdio
- Command:
/absolute/path/to/jira-mcp-server/dist/jira-mcp-server
- Set the environment variables in Cursor's settings
Claude Code
claude mcp add jira /absolute/path/to/jira-mcp-server/dist/jira-mcp-server
Tool Reference
jira-search-issues
Searches for Jira issues using a JQL query. Returns a list of matching issues with key fields.
| Parameter | Type | Required | Description |
|---|---|---|---|
jql |
string |
Yes | JQL query string |
maxResults |
number |
No | Maximum results to return (1–100, default 20) |
JQL examples:
project = MYPROJ AND status = "In Progress"
assignee = currentUser() AND sprint in openSprints()
project = MYPROJ AND labels = "backend" ORDER BY created DESC
Example response:
{
"success": true,
"total": 42,
"returned": 20,
"issues": [
{
"key": "PROJ-123",
"summary": "Fix login button on mobile",
"status": "In Progress",
"priority": "High",
"issueType": "Bug",
"assignee": "Jane Doe",
"reporter": "John Smith",
"labels": ["mobile", "frontend"],
"created": "2026-02-19T10:00:00.000+0000",
"updated": "2026-02-19T12:30:00.000+0000",
"url": "https://your-domain.atlassian.net/browse/PROJ-123"
}
]
}
jira-get-issue
Fetches an existing Jira issue by its key.
| Parameter | Type | Required | Description |
|---|---|---|---|
issueKey |
string |
Yes | The issue key (e.g. "PROJ-123") |
Example response:
{
"success": true,
"issue": {
"key": "PROJ-123",
"summary": "Fix login button on mobile",
"status": "In Progress",
"priority": "High",
"issueType": "Bug",
"assignee": "Jane Doe",
"reporter": "John Smith",
"labels": ["mobile", "frontend"],
"description": { "type": "doc", "version": 1, "content": [] },
"created": "2026-02-19T10:00:00.000+0000",
"updated": "2026-02-19T12:30:00.000+0000",
"url": "https://your-domain.atlassian.net/browse/PROJ-123"
}
}
jira-update-issue
Updates an existing Jira issue's summary and/or description. At least one field must be provided.
| Parameter | Type | Required | Description |
|---|---|---|---|
issueKey |
string |
Yes | The issue key (e.g. "PROJ-123") |
summary |
string |
No | New summary/title for the issue |
description |
string or ADF |
No | Plain text or pre-formatted ADF |
Example response:
{
"success": true,
"issue": {
"key": "PROJ-123",
"url": "https://your-domain.atlassian.net/browse/PROJ-123"
},
"message": "Successfully updated issue PROJ-123"
}
jira-create-issue
Creates a new issue in Jira.
| Parameter | Type | Required | Description |
|---|---|---|---|
summary |
string |
Yes | Summary/title of the issue |
description |
string or ADF |
No | Plain text or pre-formatted ADF object |
issueType |
string |
No | Issue type (default: "Task") |
priority |
string |
No | Priority level ("Highest", "High", "Medium", "Low", "Lowest") |
labels |
string[] |
No | Labels to add to the issue |
projectKey |
string |
No | Override the default project key |
parentKey |
string |
No | Parent issue key (e.g. "PROJ-10") — creates as a child issue |
Description formatting:
Plain text is converted to ADF paragraphs automatically:
"description": "Main description.\n\nAnother paragraph."
For full formatting control, pass a pre-formatted ADF object:
"description": {
"type": "doc",
"version": 1,
"content": [
{ "type": "paragraph", "content": [{ "type": "text", "text": "Main description" }] },
{ "type": "heading", "attrs": { "level": 3 }, "content": [{ "type": "text", "text": "TODO" }] },
{ "type": "panel", "attrs": { "panelType": "error" }, "content": [
{ "type": "paragraph", "content": [{ "type": "text", "text": "First task" }] }
]}
]
}
Panel types: error (red), info (blue), warning (yellow), success (green), note (purple).
Example response:
{
"success": true,
"issue": {
"id": "10001",
"key": "PROJ-123",
"url": "https://your-domain.atlassian.net/browse/PROJ-123"
},
"message": "Successfully created issue PROJ-123"
}
Example Commands
jira-ticket
An interactive command for drafting and creating Jira tickets with proper ADF formatting. Supports Stories, Bugs, and Maintenance tasks with a smart question flow and automatic ADF construction.
Location: command/jira-ticket.md
/jira-ticket [optional summary]
Project Structure
jira-mcp-server/
├── src/
│ ├── index.ts # Entry point, orchestrates startup
│ ├── config.ts # Environment variable validation
│ ├── server.ts # MCP server setup and tool registration
│ ├── jira-client.ts # Jira REST API client
│ ├── adf-schema.ts # Zod schema for ADF validation
│ ├── adf-schema.test.ts # ADF validation tests
│ ├── types.ts # TypeScript type definitions
│ ├── help.ts # Help text display
│ └── version.ts # Version from package.json
├── dist/
│ └── jira-mcp-server # Standalone executable (after build)
├── command/
│ └── jira-ticket.md # Interactive ticket creation command
├── biome.json # Linter/formatter configuration
└── package.json
Available Scripts
| Script | Description |
|---|---|
build |
Build standalone executable with Bun runtime included |
deploy |
Build and copy executable to ~/bin directory |
deploy-and-sign |
Build, copy, and ad-hoc sign (required on macOS) |
dev |
Run source directly with Bun (for development) |
test |
Run tests with Bun |
lint |
Check code with Biome (lint + format) |
lint:fix |
Auto-fix lint and format issues |
mcp-inspect |
Build and launch MCP Inspector for manual testing |
Future Improvements
- [ ] Add more Jira operations (delete, search, comment, transitions)
- [ ] Support for custom fields
- [ ] Support for attachments
- [ ] Caching of project/issue type metadata
- [ ] Support for Jira Server/Data Center (different auth method)
- [ ] Add assignee field support
- [ ] Add component support
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。