Elevance MCP Atlassian Server
Provides Jira and Confluence integration for AI assistants, enabling natural language management of issues, projects, sprints, pages, comments, attachments, and more with 72 tools.
README
Elevance MCP Atlassian - Standalone Package
Model Context Protocol server for Jira and Confluence integration with AI assistants.
What This Provides
72 Tools Total:
- 48 Jira tools (search, create, update, transitions, comments, etc.)
- 24 Confluence tools (search, pages, comments, attachments, etc.)
Quick Setup (5 Minutes)
1. Get Your Personal Access Token (PAT)
Jira & Confluence:
- Login to https://jira.elevancehealth.com
- Click Profile Icon → Profile
- Navigate to "Personal Access Tokens"
- Click "Create Token"
- Name:
MCP Atlassian Integration - Expiry: 1 year
- Name:
- COPY THE TOKEN (shown only once!)
2. Configure Environment
# Copy template
copy .env.template .env
# Edit .env and paste your PAT tokens
notepad .env
Replace YOUR_JIRA_PAT_TOKEN_HERE and YOUR_CONFLUENCE_PAT_TOKEN_HERE with your actual token.
3. Install Dependencies
# Option A: Using pip
pip install -r requirements.txt
# Option B: Install as package
pip install -e .
4. Configure Your IDE
For Claude Desktop:
Edit %APPDATA%\Claude\claude_desktop_config.json:
{
"mcpServers": {
"elevance-atlassian": {
"command": "python",
"args": ["-m", "mcp_atlassian"],
"cwd": "C:\\path\\to\\elevance-mcp-atlassian-standalone",
"env": {
"JIRA_URL": "https://jira.elevancehealth.com",
"JIRA_PERSONAL_TOKEN": "YOUR_PAT_HERE",
"CONFLUENCE_URL": "https://confluence.elevancehealth.com/",
"CONFLUENCE_PERSONAL_TOKEN": "YOUR_PAT_HERE"
}
}
}
}
For Windsurf:
Add to your MCP settings or use the .env file approach (recommended).
For Cursor:
Add to MCP configuration in settings, similar format as Claude Desktop.
5. Test Connection
python validate_setup.py
You should see all checks passing with ✅ symbols.
6. Start Using!
Restart your IDE and ask your AI assistant:
- "Find my assigned Jira issues"
- "Search Confluence for onboarding docs"
- "Create a bug in project XYZ"
- "Update PROJ-123 status to In Progress"
- "Show me issues in the current sprint"
- "Get page content from Confluence space DEV"
Available Tools
Jira Tools (48)
Search & Discovery:
jira_search- Search issues with JQLjira_search_fields- Find custom field definitionsjira_get_all_projects- List accessible projectsjira_get_project_issues- Get all issues in project
Issue Management:
jira_get_issue- Get issue detailsjira_create_issue- Create new issuejira_update_issue- Update existing issuejira_delete_issue- Delete issuejira_batch_create_issues- Create multiple issues
Status & Workflow:
jira_transition_issue- Change issue statusjira_get_transitions- Get available transitions
Comments:
jira_add_comment- Add comment to issuejira_edit_comment- Edit existing comment
Links:
jira_create_issue_link- Link two issuesjira_remove_issue_link- Remove linkjira_create_remote_issue_link- Create web linkjira_link_to_epic- Link issue to epicjira_get_link_types- Get available link types
Attachments:
jira_download_attachments- Download issue attachmentsjira_get_issue_images- Get images as inline content
Watchers:
jira_add_watcher- Add watcher to issuejira_remove_watcher- Remove watcherjira_get_issue_watchers- List watchers
Time Tracking:
jira_add_worklog- Log work on issuejira_get_worklog- Get worklog entries
Agile/Sprints:
jira_get_agile_boards- List boardsjira_get_board_issues- Get issues on boardjira_get_sprints_from_board- List sprintsjira_get_sprint_issues- Get issues in sprintjira_create_sprint- Create new sprintjira_update_sprint- Update sprintjira_add_issues_to_sprint- Add issues to sprint
Versions:
jira_get_project_versions- List versionsjira_create_version- Create new versionjira_batch_create_versions- Create multiple versions
Components:
jira_get_project_components- List project components
Analytics:
jira_get_issue_dates- Get date informationjira_get_issue_sla- Calculate SLA metricsjira_batch_get_changelogs- Get change history
Development Info:
jira_get_issue_development_info- Get PRs, commits, branchesjira_get_issues_development_info- Batch development info
Advanced:
jira_get_user_profile- Get user informationjira_get_field_options- Get custom field optionsjira_get_issue_proforma_forms- Get ProForma formsjira_get_proforma_form_details- Get form detailsjira_update_proforma_form_answers- Update form answers
Service Desk (Server/DC only):
jira_get_service_desk_for_project- Get service deskjira_get_service_desk_queues- List queuesjira_get_queue_issues- Get issues in queue
Confluence Tools (24)
Search:
confluence_search- Search content with CQLconfluence_search_user- Search users
Pages:
confluence_get_page- Get page contentconfluence_create_page- Create new pageconfluence_update_page- Update pageconfluence_delete_page- Delete pageconfluence_move_page- Move pageconfluence_get_page_children- Get child pagesconfluence_get_page_history- Get page versionconfluence_get_page_diff- Compare versions
Comments:
confluence_add_comment- Add commentconfluence_reply_to_comment- Reply to commentconfluence_get_comments- Get page comments
Attachments:
confluence_get_attachments- List attachmentsconfluence_upload_attachment- Upload fileconfluence_upload_attachments- Upload multiple filesconfluence_download_attachment- Download fileconfluence_download_content_attachments- Download all attachmentsconfluence_delete_attachment- Delete attachment
Images:
confluence_get_page_images- Get images as inline content
Labels:
confluence_get_labels- Get content labelsconfluence_add_label- Add label
Analytics:
confluence_get_page_views- Get view statistics
Troubleshooting
"Module not found" error
pip install -e .
"Authentication failed"
- Verify PAT token is valid and not expired
- Check token hasn't been revoked
- Ensure correct URL (https://jira.elevancehealth.com)
- Try regenerating the token
SSL Certificate errors
Add to .env file:
JIRA_SSL_VERIFY=false
CONFLUENCE_SSL_VERIFY=false
Connection test fails
# Test if Python can import the module
python -c "import mcp_atlassian; print('OK')"
# Check MCP version
python -m mcp_atlassian --version
"No such file or directory" when running validation
Make sure you're in the correct directory:
cd C:\path\to\elevance-mcp-atlassian-standalone
python validate_setup.py
Tools not appearing in IDE
- Verify IDE configuration has correct paths
- Restart IDE completely
- Check IDE logs for MCP connection errors
- Ensure
TOOLSETS=allin.envor IDE config
Security Best Practices
- ✅ Keep your
.envfile private - ✅ Never share PAT tokens
- ✅ Rotate tokens every 6-12 months
- ✅ Don't commit
.envto version control - ✅ Use strong token names for tracking
- ✅ Revoke tokens when no longer needed
Advanced Configuration
Filter to Specific Projects
In .env:
JIRA_PROJECTS_FILTER=PROJ1,PROJ2,PROJ3
CONFLUENCE_SPACES_FILTER=SPACE1,SPACE2,SPACE3
Enable Verbose Logging
In .env:
MCP_VERBOSE=true
MCP_VERY_VERBOSE=true # Debug level
Read-Only Mode (Testing)
In .env:
READ_ONLY_MODE=true
This prevents any write operations (create, update, delete).
Custom Toolsets
In .env:
# Only core tools
TOOLSETS=default
# Specific toolsets
TOOLSETS=default,jira_agile,jira_analytics
# Specific tools only
ENABLED_TOOLS=jira_search,jira_get_issue,confluence_search
System Requirements
- Python: 3.10 or higher
- Operating System: Windows, macOS, or Linux
- Network: Access to jira.elevancehealth.com
- IDE: Claude Desktop, Cursor, or Windsurf with MCP support
Package Contents
elevance-mcp-atlassian-standalone/
├── src/mcp_atlassian/ # Complete MCP implementation
│ ├── jira/ # 48 Jira tools
│ ├── confluence/ # 24 Confluence tools
│ ├── models/ # Data models
│ ├── servers/ # MCP server logic
│ └── utils/ # Utilities
├── .env.template # Configuration template
├── requirements.txt # Python dependencies
├── pyproject.toml # Package metadata
├── validate_setup.py # Setup validation script
├── README.md # This file
├── SETUP-GUIDE.md # Detailed setup instructions
└── LICENSE # MIT License
Support
For issues or questions, contact:
- Developer: Mohamed Wasim
- Email: Mohamed.Wasim@carelon.com
Next Steps
- ✅ Complete setup using steps above
- ✅ Run validation:
python validate_setup.py - ✅ Configure your IDE
- ✅ Restart IDE
- ✅ Start using AI assistant with Jira/Confluence
Additional Resources
- SETUP-GUIDE.md - Detailed step-by-step guide with screenshots descriptions
- Original Documentation - https://mcp-atlassian.soomiles.com
License
MIT License - Internal use for Elevance Health/Carelon
Version: 1.0
Last Updated: March 2026
Maintained by: Carelon Global Solutions
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.