Atlassian / Community
Jira MCP Server
MCP server that connects AI coding agents to Jira for searching issues, creating and updating tickets, reading comments, and pulling acceptance criteria into development workflows.
Last reviewed Feb 28, 2026
What it does
Jira MCP servers connect AI coding agents to Jira Cloud, Server, or Data Center. Agents can search issues via JQL, fetch issue details and relationships, create and update issues, add comments, and pull acceptance criteria into implementation work. Atlassian offers an official remote MCP server with OAuth 2.1; community servers use API tokens with stdio transport.
Available tools
| Tool | What it does |
|---|---|
jira_search_issues |
Search issues with JQL queries |
jira_get_issue |
Get full issue details including description and comments |
jira_create_issue |
Create a new issue with project, type, summary, description |
jira_update_issue |
Update issue status, assignee, or other fields |
jira_add_comment |
Add a comment to an issue |
jira_get_transitions |
Get available workflow transitions |
jira_list_projects |
List projects in the instance |
Tool names vary by implementation. Atlassian's official server may use different naming.
Setup by tool
Cursor (community stdio server)
Create .cursor/mcp.json:
{
"mcpServers": {
"jira": {
"command": "npx",
"args": ["-y", "@timbreeding/jira-mcp-server"],
"env": {
"JIRA_BASE_URL": "https://your-domain.atlassian.net",
"JIRA_USERNAME": "user@example.com",
"JIRA_API_TOKEN": "your_api_token"
}
}
}
}
Cursor (Atlassian remote OAuth)
If using Atlassian's hosted MCP server, add the URL and follow the OAuth flow when prompted. Check the Atlassian MCP documentation for the current endpoint.
Claude Code
Add the same configuration to your Claude MCP config. For API token auth, ensure JIRA_BASE_URL, JIRA_USERNAME, and JIRA_API_TOKEN are set in env.
VS Code / GitHub Copilot
Add the server to your MCP client with the appropriate command and env vars.
Getting a Jira API token
- Log in to id.atlassian.com
- Click Create API token
- Name it (e.g., "MCP Agent") and copy the token
- Use your Atlassian account email as
JIRA_USERNAME
When to use this
- Issue-driven development: Agents read acceptance criteria before implementing
- Status updates: Update ticket status when work is complete
- Context gathering: Search related issues to understand constraints and prior decisions
- Sprint support: Reference backlog and project progress during planning
Security considerations
- API tokens grant the same access as your user; use a service account for shared agents
- Prefer Atlassian's OAuth server when available for finer-grained control
- Limit JQL scope when possible; broad searches may expose sensitive issues
- Do not commit API tokens; use environment variables
- Review agent-created comments and status changes in Jira's audit log
Compatibility
Related MCP servers
AWS MCP Server
Open source MCP servers from AWS Labs that give AI coding agents access to AWS documentation, best practices, and contextual guidance for building on AWS.
Docker MCP Server
Docker MCP Gateway orchestrates MCP servers in isolated containers, providing secure discovery and execution of Model Context Protocol servers across AI coding tools.
Figma MCP Server
Official Figma MCP server that brings design context, variables, components, and Code Connect data into AI coding sessions for design-to-code workflows.