MCP Now
Atlassian

Atlassian

by sooperset
GitHub

Interact with Atlassian Cloud products (Confluence and Jira) including searching/reading Confluence spaces/pages, accessing Jira issues, and project metadata.

confluence
jira
cloud
uvx
issue

MCP Atlassian

PyPI Version PyPI - Downloads PePy - Total Downloads License

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

Jira Demo

Confluence Demo

Confluence Demo

Compatibility

| Product | Deployment Type | Support Status | |---------|----------------|-----------------------------| | Confluence | Cloud | ✅ Fully supported | | Confluence | Server/Data Center | ✅ Supported (version 7.9+) | | Jira | Cloud | ✅ Fully supported | | Jira | Server/Data Center | ✅ Supported (version 8.14+) |

Setup Guide

1. Authentication Setup

First, generate the necessary authentication tokens for Confluence & Jira:

For Cloud

  1. Go to https://id.atlassian.com/manage-profile/security/api-tokens
  2. Click Create API token, name it
  3. Copy the token immediately

For Server/Data Center

  1. Go to your profile (avatar) → ProfilePersonal Access Tokens
  2. Click Create token, name it, set expiry
  3. Copy the token immediately

2. Installation

Choose one of these installation methods:

1# Using uv (recommended) 2brew install uv 3uvx mcp-atlassian 4 5# Using pip 6pip install mcp-atlassian 7 8# Using Docker 9git clone https://github.com/sooperset/mcp-atlassian.git 10cd mcp-atlassian 11docker build -t mcp/atlassian .

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:

1uvx mcp-atlassian \ 2 --confluence-url https://your-company.atlassian.net/wiki \ 3 --confluence-username [email protected] \ 4 --confluence-token your_api_token \ 5 --jira-url https://your-company.atlassian.net \ 6 --jira-username [email protected] \ 7 --jira-token your_api_token

For Server/Data Center:

1uvx mcp-atlassian \ 2 --confluence-url https://confluence.your-company.com \ 3 --confluence-personal-token your_token \ 4 --jira-url https://jira.your-company.com \ 5 --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] or sse)
  • --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:

1{ 2 "mcpServers": { 3 "mcp-atlassian": { 4 "command": "uvx", 5 "args": [ 6 "mcp-atlassian", 7 "--confluence-url=https://your-company.atlassian.net/wiki", 8 "[email protected]", 9 "--confluence-token=your_api_token", 10 "--jira-url=https://your-company.atlassian.net", 11 "[email protected]", 12 "--jira-token=your_api_token" 13 ] 14 } 15 } 16}
Using uvx (recommended) - Server/Data Center
1{ 2 "mcpServers": { 3 "mcp-atlassian": { 4 "command": "uvx", 5 "args": [ 6 "mcp-atlassian", 7 "--confluence-url=https://confluence.your-company.com", 8 "--confluence-personal-token=your_token", 9 "--jira-url=https://jira.your-company.com", 10 "--jira-personal-token=your_token" 11 ] 12 } 13 } 14}
Using pip

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.

1{ 2 "mcpServers": { 3 "mcp-atlassian": { 4 "command": "python", 5 "args": [ 6 "-m", 7 "mcp-atlassian", 8 "--confluence-url=https://your-company.atlassian.net/wiki", 9 "[email protected]", 10 "--confluence-token=your_api_token", 11 "--jira-url=https://your-company.atlassian.net", 12 "[email protected]", 13 "--jira-token=your_api_token" 14 ] 15 } 16 } 17}
Using docker

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:

  1. Using cli arguments directly in the config:
1{ 2 "mcpServers": { 3 "mcp-atlassian": { 4 "command": "docker", 5 "args": [ 6 "run", 7 "--rm", 8 "-i", 9 "mcp/atlassian", 10 "--confluence-url=https://your-company.atlassian.net/wiki", 11 "[email protected]", 12 "--confluence-token=your_api_token", 13 "--jira-url=https://your-company.atlassian.net", 14 "[email protected]", 15 "--jira-token=your_api_token" 16 ] 17 } 18 } 19}
  1. Using an environment file:
1{ 2 "mcpServers": { 3 "mcp-atlassian": { 4 "command": "docker", 5 "args": [ 6 "run", 7 "--rm", 8 "-i", 9 "--env-file", 10 "/path/to/your/.env", 11 "mcp/atlassian" 12 ] 13 } 14 } 15}

Cursor IDE Setup

  1. Open Cursor Settings
  2. Navigate to Features > MCP Servers (or directly to MCP)
  3. Click + Add new global MCP server

This will create or edit the ~/.cursor/mcp.json file with your MCP server configuration.

Cursor MCP Configuration

JSON Configuration for stdio Transport

For Cloud:

1{ 2 "mcpServers": { 3 "mcp-atlassian": { 4 "command": "uvx", 5 "args": [ 6 "mcp-atlassian", 7 "--confluence-url=https://your-company.atlassian.net/wiki", 8 "[email protected]", 9 "--confluence-token=your_api_token", 10 "--jira-url=https://your-company.atlassian.net", 11 "[email protected]", 12 "--jira-token=your_api_token" 13 ] 14 } 15 } 16}
Server/Data Center Configuration
1{ 2 "mcpServers": { 3 "mcp-atlassian": { 4 "command": "uvx", 5 "args": [ 6 "mcp-atlassian", 7 "--confluence-url=https://confluence.your-company.com", 8 "--confluence-personal-token=your_token", 9 "--jira-url=https://jira.your-company.com", 10 "--jira-personal-token=your_token" 11 ] 12 } 13 } 14}

SSE Transport Configuration

For SSE transport, first start the server:

1uvx mcp-atlassian --transport sse --port 9000

Then configure in Cursor:

1{ 2 "mcpServers": { 3 "mcp-atlassian-sse": { 4 "url": "http://localhost:9000/sse", 5 "env": { 6 "CONFLUENCE_URL": "https://your-company.atlassian.net/wiki", 7 "CONFLUENCE_USERNAME": "[email protected]", 8 "CONFLUENCE_API_TOKEN": "your_api_token", 9 "JIRA_URL": "https://your-company.atlassian.net", 10 "JIRA_USERNAME": "[email protected]", 11 "JIRA_API_TOKEN": "your_api_token" 12 } 13 } 14 } 15}

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 spaces
  • jira://{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 | | 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_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_worklog | Add a worklog entry to a Jira issue | | jira_get_worklog | Get worklog entries for a Jira issue | | jira_link_to_epic | Link an issue to an Epic | | jira_get_epic_issues | Get all issues linked to a specific Epic |

Development & Debugging

Local Development Setup

If you've cloned the repository and want to run a local version:

For Cloud:

1{ 2 "mcpServers": { 3 "mcp-atlassian": { 4 "command": "uv", 5 "args": [ 6 "--directory", "/path/to/your/mcp-atlassian", 7 "run", "mcp-atlassian", 8 "--confluence-url=https://your-domain.atlassian.net/wiki", 9 "[email protected]", 10 "--confluence-token=your_api_token", 11 "--jira-url=https://your-domain.atlassian.net", 12 "[email protected]", 13 "--jira-token=your_api_token" 14 ] 15 } 16 } 17}

Debugging Tools

1# Using MCP Inspector 2# For installed package 3npx @modelcontextprotocol/inspector uvx mcp-atlassian ... 4 5# For local development version 6npx @modelcontextprotocol/inspector uv --directory /path/to/your/mcp-atlassian run mcp-atlassian ... 7 8# View logs 9tail -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.