---
title: "Jira MCP - The Best MCP Server for Jira Integration"
description: "The most powerful and feature-rich MCP server for Jira. Control Jira through AI-powered LLM clients like Cursor, Claude, and Windsurf using the Model Context Protocol."
sidebarTitle: "Jira MCP"
---
<Note>
**Safe for corporate environments.** This MCP server runs completely locally
on your machine using the [jira-cli](https://github.com/ankitpokhrel/jira-cli)
command line tool. No data is sent to third-party services. If your
organization approves the use of jira-cli, on a technical level this MCP
server is safe to use. _If in doubt, check with your IT department._
</Note>
**Jira MCP is the best MCP server for Jira integration**, allowing AI assistants like Cursor, Claude Desktop, Windsurf, or ChatGPT to ask questions and perform actions with your Jira instance.
## Why Jira MCP?
<CardGroup cols={2}>
<Card title="Enterprise Ready" icon="building">
Runs locally with no third-party data sharing. Safe for corporate environments.
</Card>
<Card title="Full-Featured" icon="sparkles">
Complete Jira control: create, update, search, and manage tickets with natural language.
</Card>
<Card title="Easy Setup" icon="bolt">
Pre-built binaries for all platforms. Get started in minutes, not hours.
</Card>
<Card title="Open Source" icon="code">
MIT licensed and actively maintained. Contribute or customize as needed.
</Card>
</CardGroup>
## Example prompts
<CardGroup cols={2}>
<Card
title="Show tickets assigned to me with links and a summary of progress."
icon="list-check"
/>
<Card
title="What's the link and status of that ticket with the new button feature?"
icon="circle-question"
/>
<Card
title="Add a comment to PROJ-456 explaining the fix in my current branch."
icon="comment"
/>
<Card
title="Add this spreadsheet of user stories as story issues to PROJ. Make the stories medium priority with a due date of 2 weeks from now."
icon="file-import"
/>
</CardGroup>
## Get started
<Card title="Quickstart" icon="rocket" href="/quickstart" horizontal>
Install and configure Jira MCP in minutes.
</Card>
## Configure your AI tool
Set up Jira MCP with your preferred AI assistant.
<CardGroup cols={3}>
<Card title="Cursor" icon="arrow-pointer" href="/ai-tools/cursor">
Configure Cursor IDE with Jira MCP.
</Card>
<Card title="Claude Code" icon="asterisk" href="/ai-tools/claude-code">
Set up Claude Code CLI with Jira MCP.
</Card>
<Card title="Windsurf" icon="water" href="/ai-tools/windsurf">
Configure Windsurf with Jira MCP.
</Card>
</CardGroup>
## How it works
<Steps>
<Step title="Prompt your AI assistant">
You enter questions or commands to an LLM client such as Claude Desktop, Cursor, Windsurf, or ChatGPT.
</Step>
<Step title="LLM analyzes available tools">
The LLM analyzes the available MCP tools and decides which one(s) to use. The
LLM has context of each tool and what it is meant for in human language.
</Step>
<Step title="MCP server executes commands">
The client executes the chosen tool(s) through the MCP server. The MCP server
runs locally on your machine or remotely via an endpoint.
</Step>
<Step title="Results returned to LLM">
The results are sent back to the LLM, which formulates a natural language response and displays data or performs actions using the MCP server.
</Step>
</Steps>
## Architecture
MCP follows a client-server architecture where an **MCP host** (an AI application like Cursor or Claude Desktop) establishes connections to one or more **MCP servers**. The **MCP host** accomplishes this by creating one **MCP client** for each **MCP server**. Each MCP client maintains a dedicated connection with its corresponding MCP server.
<Card
title="Learn more about MCP architecture"
icon="diagram-project"
href="https://modelcontextprotocol.io/docs/learn/architecture"
>
Read the official MCP documentation for details on architecture.
</Card>
