MCP Atlassian
by sooperset
MCP server that integrates Confluence and Jira
What is MCP Atlassian
MCP Atlassian
Model Context Protocol (MCP) server for Atlassian products (Confluence and Jira). This integration supports both Confluence & Jira Cloud and Server/Data Center deployments.
Feature Demo
https://github.com/user-attachments/assets/7fe9c488-ad0c-4876-9b54-120b666bb785
Compatibility
Product | Deployment Type | Support Status |
---|---|---|
Confluence | Cloud | โ Fully supported |
Confluence | Server/Data Center | โ Supported (version 6.0+) |
Jira | Cloud | โ Fully supported |
Jira | Server/Data Center | โ Supported (version 8.14+) |
Setup Guide
1. Authentication Setup
First, generate the necessary authentication tokens for Confluence & Jira:
For Cloud
- Go to https://id.atlassian.com/manage-profile/security/api-tokens
- Click Create API token, name it
- Copy the token immediately
For Server/Data Center
- Go to your profile (avatar) โ Profile โ Personal Access Tokens
- Click Create token, name it, set expiry
- Copy the token immediately
2. Installation
Choose one of these installation methods:
# Using uv (recommended)
brew install uv
uvx mcp-atlassian
# Using pip
pip install mcp-atlassian
# Using Docker
git clone https://github.com/sooperset/mcp-atlassian.git
cd mcp-atlassian
docker build -t mcp/atlassian .
# Using Smithery
npx -y @smithery/cli install mcp-atlassian --client claude
3. Configuration and Usage
You can configure the MCP server using command line arguments. The server supports using either Confluence, Jira, or both services - include only the arguments needed for your use case.
Required Arguments
For Cloud:
uvx mcp-atlassian \
--confluence-url https://your-company.atlassian.net/wiki \
--confluence-username [email protected] \
--confluence-token your_api_token \
--jira-url https://your-company.atlassian.net \
--jira-username [email protected] \
--jira-token your_api_token
For Server/Data Center:
uvx mcp-atlassian \
--confluence-url https://confluence.your-company.com \
--confluence-personal-token your_token \
--jira-url https://jira.your-company.com \
--jira-personal-token your_token
Note: You can configure just Confluence, just Jira, or both services. Simply include only the arguments for the service(s) you want to use. For example, to use only Confluence Cloud, you would only need
--confluence-url
,--confluence-username
, and--confluence-token
.
Optional Arguments
--transport
: Choose transport type (stdio
[default] orsse
)--port
: Port number for SSE transport (default: 8000)--[no-]confluence-ssl-verify
: Toggle SSL verification for Confluence Server/DC--[no-]jira-ssl-verify
: Toggle SSL verification for Jira Server/DC--confluence-spaces-filter
: Comma-separated list of space keys to filter Confluence search results (e.g., "DEV,TEAM,DOC")--jira-projects-filter
: Comma-separated list of project keys to filter Jira search results (e.g., "PROJ,DEV,SUPPORT")--read-only
: Run in read-only mode (disables all write operations)--verbose
: Increase logging verbosity (can be used multiple times, default is WARNING level)-v
or--verbose
: Set logging to INFO level-vv
or--verbose --verbose
: Set logging to DEBUG level
Note: All configuration options can also be set via environment variables. See the
.env.example
file in the repository for the full list of available environment variables.
IDE Integration
Claude Desktop Setup
Using uvx (recommended) - Cloud:
{
"mcpServers": {
"mcp-atlassian": {
"command": "uvx",
"args": [
"mcp-atlassian",
"--confluence-url=https://your-company.atlassian.net/wiki",
"[email protected]",
"--confluence-token=your_api_token",
"--jira-url=https://your-company.atlassian.net",
"[email protected]",
"--jira-token=your_api_token"
]
}
}
}
{
"mcpServers": {
"mcp-atlassian": {
"command": "uvx",
"args": [
"mcp-atlassian",
"--confluence-url=https://confluence.your-company.com",
"--confluence-personal-token=your_token",
"--jira-url=https://jira.your-company.com",
"--jira-personal-token=your_token"
]
}
}
}
{
"mcpServers": {
"mcp-atlassian": {
"command": "uvx",
"args": [
"mcp-atlassian",
"--confluence-url=https://confluence.your-company.com",
"[email protected]",
"--confluence-token=your_password"
]
}
}
}
{
"mcpServers": {
"mcp-atlassian": {
"command": "uvx",
"args": [
"mcp-atlassian",
"--confluence-url=https://your-company.atlassian.net/wiki",
"[email protected]",
"--confluence-token=your_api_token"
]
}
}
}
{
"mcpServers": {
"mcp-atlassian": {
"command": "uvx",
"args": [
"mcp-atlassian",
"--jira-url=https://your-company.atlassian.net",
"[email protected]",
"--jira-token=your_api_token"
]
}
}
}
Note: Examples below use Cloud configuration. For Server/Data Center, use the corresponding arguments (--confluence-personal-token, --jira-personal-token) as shown in the Configuration section above.
{
"mcpServers": {
"mcp-atlassian": {
"command": "mcp-atlassian",
"args": [
"--confluence-url=https://your-company.atlassian.net/wiki",
"[email protected]",
"--confluence-token=your_api_token",
"--jira-url=https://your-company.atlassian.net",
"[email protected]",
"--jira-token=your_api_token"
]
}
}
}
Note: Examples below use Cloud configuration. For Server/Data Center, use the corresponding arguments (--confluence-personal-token, --jira-personal-token) as shown in the Configuration section above.
There are two ways to configure the Docker environment:
- Using cli arguments directly in the config:
{
"mcpServers": {
"mcp-atlassian": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"mcp/atlassian",
"--confluence-url=https://your-company.atlassian.net/wiki",
"[email protected]",
"--confluence-token=your_api_token",
"--jira-url=https://your-company.atlassian.net",
"[email protected]",
"--jira-token=your_api_token"
]
}
}
}
- Using an environment file:
{
"mcpServers": {
"mcp-atlassian": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"--env-file",
"/path/to/your/.env",
"mcp/atlassian"
]
}
}
}
Cursor IDE Setup
- Open Cursor Settings
- Navigate to
Features
>MCP Servers
(or directly toMCP
) - Click
+ Add new global MCP server
This will create or edit the ~/.cursor/mcp.json
file with your MCP server configuration.
JSON Configuration for stdio Transport
For Cloud:
{
"mcpServers": {
"mcp-atlassian": {
"command": "uvx",
"args": [
"mcp-atlassian",
"--confluence-url=https://your-company.atlassian.net/wiki",
"[email protected]",
"--confluence-token=your_api_token",
"--jira-url=https://your-company.atlassian.net",
"[email protected]",
"--jira-token=your_api_token"
]
}
}
}
{
"mcpServers": {
"mcp-atlassian": {
"command": "uvx",
"args": [
"mcp-atlassian",
"--confluence-url=https://confluence.your-company.com",
"--confluence-personal-token=your_token",
"--jira-url=https://jira.your-company.com",
"--jira-personal-token=your_token"
]
}
}
}
SSE Transport Configuration
For SSE transport, first start the server with its configuration provided via command-line arguments or server-side environment variables (e.g., from a .env
file):
# Example starting the server with Cloud configuration
uvx mcp-atlassian --transport sse --port 9000 \
--confluence-url https://your-company.atlassian.net/wiki \
--confluence-username [email protected] \
--confluence-token your_api_token \
--jira-url https://your-company.atlassian.net \
--jira-username [email protected] \
--jira-token your_api_token
Then configure only the URL in Cursor's ~/.cursor/mcp.json
:
{
"mcpServers": {
"mcp-atlassian-sse": {
"url": "http://localhost:9000/sse"
}
}
}
Resources
Note: The MCP server filters resources to only show Confluence spaces and Jira projects that the user is actively interacting with, based on their contributions and assignments.
confluence://{space_key}
: Access Confluence spacesjira://{project_key}
: Access Jira projects
Available Tools
Tool | Description |
---|---|
confluence_search |
Search Confluence content using CQL |
confluence_get_page |
Get content of a specific Confluence page |
confluence_get_page_children |
Get child pages of a specific Confluence page |
confluence_get_page_ancestors |
Get parent pages of a specific Confluence page |
confluence_get_comments |
Get comments for a specific Confluence page |
confluence_create_page |
Create a new Confluence page |
confluence_update_page |
Update an existing Confluence page |
confluence_delete_page |
Delete an existing Confluence page |
confluence_attach_content |
Attach content to a Confluence page |
jira_get_issue |
Get details of a specific Jira issue |
jira_search |
Search Jira issues using JQL |
jira_get_project_issues |
Get all issues for a specific Jira project |
jira_get_epic_issues |
Get all issues linked to a specific Epic |
jira_create_issue |
Create a new issue in Jira |
jira_update_issue |
Update an existing Jira issue |
jira_delete_issue |
Delete an existing Jira issue |
jira_get_transitions |
Get available status transitions for a Jira issue |
jira_transition_issue |
Transition a Jira issue to a new status |
jira_add_comment |
Add a comment to a Jira issue |
jira_add_worklog |
Add a worklog entry to a Jira issue |
jira_get_worklog |
Get worklog entries for a Jira issue |
jira_download_attachments |
Download attachments from a Jira issue |
jira_link_to_epic |
Link an issue to an Epic |
jira_get_agile_boards |
Get Jira agile boards by name, project key, or type |
jira_get_board_issues |
Get all issues linked to a specific board |
jira_get_sprints_from_board |
Get Jira sprints from board by state |
jira_get_sprint_issues |
Get Jira issues from sprint |
Development & Debugging
Local Development Setup
If you've cloned the repository and want to run a local version:
For Cloud:
{
"mcpServers": {
"mcp-atlassian": {
"command": "uv",
"args": [
"--directory", "/path/to/your/mcp-atlassian",
"run", "mcp-atlassian",
"--confluence-url=https://your-domain.atlassian.net/wiki",
"[email protected]",
"--confluence-token=your_api_token",
"--jira-url=https://your-domain.atlassian.net",
"[email protected]",
"--jira-token=your_api_token"
]
}
}
}
Debugging Tools
# Using MCP Inspector
# For installed package
npx @modelcontextprotocol/inspector uvx mcp-atlassian ...
# For local development version
npx @modelcontextprotocol/inspector uv --directory /path/to/your/mcp-atlassian run mcp-atlassian ...
# View logs
tail -n 20 -f ~/Library/Logs/Claude/mcp*.log
Security
- Never share API tokens
- Keep .env files secure and private
- See SECURITY.md for best practices
License
Licensed under MIT - see LICENSE file. This is not an official Atlassian product.
Leave a Comment
Comments section will be available soon. Stay tuned!
Frequently Asked Questions
What is MCP?
MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications, providing a standardized way to connect AI models to different data sources and tools.
What are MCP Servers?
MCP Servers are lightweight programs that expose specific capabilities through the standardized Model Context Protocol. They act as bridges between LLMs like Claude and various data sources or services, allowing secure access to files, databases, APIs, and other resources.
How do MCP Servers work?
MCP Servers follow a client-server architecture where a host application (like Claude Desktop) connects to multiple servers. Each server provides specific functionality through standardized endpoints and protocols, enabling Claude to access data and perform actions through the standardized protocol.
Are MCP Servers secure?
Yes, MCP Servers are designed with security in mind. They run locally with explicit configuration and permissions, require user approval for actions, and include built-in security features to prevent unauthorized access and ensure data privacy.
Related MCP Servers
Ableton Live MCP Server
MCP Server implementation for Ableton Live OSC control
Airbnb MCP Server
AI Agent Marketplace Index Search MCP Server
MCP Server for AI Agent Marketplace Index from DeepNLP
Algorand MCP Implementation
Algorand Model Context Protocol (Server & Client)
mcp-server-apache-airflow
pypi.org/project/mcp-server-apache-airflow/
airtable-mcp-server
๐๏ธ๐ค Airtable Model Context Protocol Server, for allowing AI systems to interact with your Airtable bases
Airtable MCP Server
Search, create and update Airtable bases, tables, fields, and records using Claude Desktop and MCP (Model Context Protocol) clients
Alphavantage MCP Server
A MCP server for the stock market data API, Alphavantage API.
Amadeus MCP Server
Amadeus MCP(Model Context Protocol) Server
Anki MCP Server
An MCP server for Anki
Submit Your MCP Server
Share your MCP server with the community
Submit Now