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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.