← Back to MCP servers

Atlassian

Jira MCP Server

Search, create, and manage Jira issues and projects from your AI coding assistant.

API key requiredGet credentials →

Last reviewed Mar 2, 2026

Install

claude mcp add jira --transport stdio -- npx -y mcp-atlassian --jira-url https://your-domain.atlassian.net --jira-username your@email.com --jira-token your-api-token
Scope: project

Available tools

ToolDescription
search_issuesSearch Jira issues using JQL queries
get_issueGet detailed information about a specific issue
create_issueCreate a new Jira issue in a project
update_issueUpdate fields on an existing issue
add_commentAdd a comment to a Jira issue

What it does

The Jira MCP Server connects your AI coding assistant to Atlassian Jira, enabling it to search, read, create, and update issues directly from your development environment. It uses JQL (Jira Query Language) for powerful search capabilities and supports the full lifecycle of issue management.

This integration is especially valuable for teams that use Jira for sprint planning and bug tracking. Your assistant can look up ticket requirements before implementing features, update issue statuses as you complete work, and create new issues when you discover bugs during development.

Use cases

  • Look up issue details and acceptance criteria while implementing features
  • Search for related issues using JQL before creating duplicates
  • Create bug reports directly from your editor when you find issues during development
  • Update issue status and add comments to keep your team informed of progress
  • Review sprint backlogs and assigned issues without switching to the Jira UI

Getting started

  1. Generate a Jira API token at id.atlassian.com/manage-profile/security/api-tokens.
  2. Replace the placeholders in the install command: set your Jira instance URL (e.g., https://yourcompany.atlassian.net), your Atlassian account email, and the API token.
  3. The MCP server uses Jira's REST API, so your account permissions determine which projects and issues the assistant can access.
  4. For read-only access, consider creating a dedicated Jira account with restricted permissions to limit the scope of what the assistant can modify.