Jira MCP Server

A Model Context Protocol (MCP) server that integrates with Jira Cloud for project management and issue tracking.

Connect your AI assistant (Claude, Cursor, VS Code, Windsurf) to Jira and manage projects, create issues, search with JQL, track sprints, and transition tickets — all through natural language.

About this MCP Server: To understand how to connect to and use this MCP server, please refer to the official Model Context Protocol documentation at mcp.apify.com ↗.

---

✨ Features

• 🔍 JQL-powered issue search — search across all projects using Jira Query Language
• 📋 Full issue management — create, read, update issues (Task, Bug, Story, Epic)
• 💬 Comment threads — add comments to issues from your AI assistant
• 🏃 Sprint tracking — list boards, view active/future sprints, check sprint goals
• 🔄 Status transitions — move issues through your workflow (To Do → In Progress → Done)
• 📊 Project overview — list all accessible projects with metadata
• 🔐 Secure authentication — uses Jira Cloud API tokens (never stored, provided per-user)

---

🔗 Connection URL

https://mcp-servers--jira-mcp-server.apify.actor/mcp?token=YOUR_APIFY_TOKEN

Replace YOUR_APIFY_TOKEN with your Apify API token.

---

🛠️ Available Tools

Tool	Description
list_projects	List all Jira projects accessible to the authenticated user
search_issues	Search issues using JQL — supports all Jira query syntax
get_issue	Get full details of an issue including description, comments, and status
create_issue	Create a new issue (Task, Bug, Story, Epic) with description, priority, and labels
update_issue	Update issue fields — summary, description, priority, labels, assignee
add_comment	Add a comment to any issue
list_sprints	List sprints for a board — filter by active, future, or closed
transition_issue	Move an issue through workflow statuses (e.g., To Do → In Progress → Done)

🌳 Decision Tree — Which tool should I use?

Need to find issues?
├── General search → search_issues (JQL)
│   Examples: "status = 'In Progress'", "assignee = currentUser()"
├── Specific issue → get_issue (by key like PROJ-123)
└── List everything → list_projects + search_issues

Need to modify something?
├── New ticket → create_issue
├── Change fields → update_issue
├── Move status → transition_issue
└── Add note → add_comment

Need sprint info?
└── list_sprints (with optional board ID)

---

🚀 Installation

Prerequisites

Before connecting, you'll need:

1. Jira Cloud account — Sign up for free
2. Jira API Token — Generate one at Atlassian API Tokens
3. Apify account — Sign up (for hosted MCP)

🖱️ Running on Cursor

Requires Cursor version 0.45.6+

For the most up-to-date configuration instructions, see Cursor MCP Server Configuration Guide ↗.

Cursor v0.48.6+:

{
  "mcpServers": {
    "jira-mcp-server": {
      "url": "https://mcp-servers--jira-mcp-server.apify.actor/mcp?token=YOUR_APIFY_TOKEN"
    }
  }
}

Cursor v0.45.6:

1. Go to Settings → Features → MCP Servers
2. Click Add New MCP Server
3. Set the URL to the Connection URL above

💻 Running on VS Code

Add to your .vscode/mcp.json:

{
  "servers": {
    "jira-mcp-server": {
      "type": "http",
      "url": "https://mcp-servers--jira-mcp-server.apify.actor/mcp?token=YOUR_APIFY_TOKEN"
    }
  }
}

🌊 Running on Windsurf

Add to your ~/.codeium/windsurf/model_config.json:

{
  "mcpServers": {
    "jira-mcp-server": {
      "serverUrl": "https://mcp-servers--jira-mcp-server.apify.actor/mcp?token=YOUR_APIFY_TOKEN"
    }
  }
}

🤖 Running on Claude Desktop

Add to your Claude Desktop config:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "jira-mcp-server": {
      "url": "https://mcp-servers--jira-mcp-server.apify.actor/mcp?token=YOUR_APIFY_TOKEN"
    }
  }
}

---

🔑 Setting Up Jira API Token

1. Go to https://id.atlassian.com/manage-profile/security/api-tokens
2. Click Create API token
3. Give it a label (e.g., "MCP Server")
4. Copy the token immediately — you won't see it again
5. Enter the token when starting the Actor on Apify Console

Note: This server works with Jira Cloud only. Jira Server and Data Center are not supported.

---

💡 Example Prompts

Once connected to your AI assistant, try these:

Prompt	Tool Used
"List all my Jira projects"	list_projects
"Find all open bugs in project MYAPP"	search_issues
"Show me the details of MYAPP-42"	get_issue
"Create a new Task in MYAPP: Fix login page alignment"	create_issue
"Move MYAPP-42 to In Progress"	transition_issue
"What's in the current sprint?"	list_sprints + search_issues
"Add a comment to MYAPP-42: Investigated — this is a CSS issue"	add_comment
"Change the priority of MYAPP-42 to High"	update_issue

---

💰 Pricing

This Actor uses the Pay per event pricing model. Each tool call is charged individually:

Event	Price per call
Actor start	$0.10
list_projects	$0.05
search_issues	$0.08
get_issue	$0.05
create_issue	$0.10
update_issue	$0.08
add_comment	$0.05
list_sprints	$0.05
transition_issue	$0.08

Plus standard Apify platform usage costs.

---

🔧 Local Development

If you want to run this server locally:

# Clone and install
git clone <repo-url>
cd jira-mcp-server
npm install

# Create local input
echo '{
  "jiraDomain": "your-site.atlassian.net",
  "jiraEmail": "your@email.com",
  "jiraApiToken": "your-api-token"
}' > .actor/INPUT.json

# Copy input to Apify local storage
mkdir -p storage/key_value_stores/default
cp .actor/INPUT.json storage/key_value_stores/default/INPUT.json

# Build and run
npm run build
node dist/main.js

Access at http://localhost:8080/mcp

---

🛡️ Security

• API tokens are never stored by the actor — they are provided per-user via Actor input
• Tokens are transmitted over HTTPS and used only for the duration of the Actor run
• The Actor runs in an isolated container on Apify's platform
• Your Jira data is never cached or shared

---

📚 References

• Model Context Protocol — Official MCP specification
• Jira Cloud REST API v3 — Atlassian API docs
• Apify MCP Server — Connect AI agents to Apify Actors
• Atlassian MCP Server — Original open-source implementation

---

Built with ❤️ by MuLIAICHI | Report an issue