logo

atlassian/atlassian-mcp-server

Official remote MCP server for Atlassian. Securely connect Jira, Confluence, Jira Service Management, Bitbucket, and Compass to Claude, ChatGPT, Cursor, VS...

Owned by Atlassian

View on GitHub ↗Jump to charts ↓Open shareable report →

atlassian/atlassian-mcp-server has 1k+ stars and 150+ forks on GitHub, is written in JavaScript, and was last pushed on Oct 10, 2026. Data as of . Signed-in members get hourly updates — create a free account.

Summary Information

Updated 41 minutes ago
Type:Plugin / ExtensionCategory(s):MCP Servers, Agent Skills & PromptsAgent Frameworks & SDKsAI Agents & LLM Apps
Added to GitGenius on October 12th, 2026
Created on August 1st, 2025
Open Issues & Pull Requests: 93 (+0)
GitHub issues: Enabled
Number of forks: 151
Total Stargazers: 1,103 (+0)
Total Subscribers: 13 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 6.2 days
Mean response time: 24.5 days
90th percentile: 82.3 days
Tracked items: 170

Most active contributors

Sign in to see contributor activity.
Sign in

Related repositories by overlapping contributors

Maintainer activity

5 people did triage or write work on this repository in the last 12 months.

Counts unlabeled, assigned, unassigned, milestoned, demilestoned, locked, unlocked over the last 12 months. These are issue and pull request events that require triage or write permission. Commits and code review are not counted. labeled and renamed are excluded because GitHub issue forms record the issue author as the actor. Figures from October 18, 2026. This count is not comparable across projects: each project's automation decides which of these events a person emits. How this is counted.

How this project is maintained

About 15% of issues opened in the past year have never received a reply. 100% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. 35% of tracked open issues have had no activity in three months. Only 58% of issues opened in the past year have been closed. Three people close 67% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 81
New in 7 days: 3
Closed in 7 days: 3
Avg open age: 108 days
Stale 30+ days: 53
Stale 90+ days: 24

Recent activity

Opened in 7 days: 3
Closed in 7 days: 3
Comments in 7 days: 3
Events in 7 days: 10

Top labels

  • enhancement (51)
  • bug (47)
  • needs-triage (28)
  • done-and-pending-feedback (15)
  • reauth (11)
  • duplicate (6)
  • invalid (4)
  • large-docs (2)

Most active issues this week

Sign in to see which issues are moving.
Sign in
Explore full issue details

Detailed Description

Atlassian MCP Server is a Model Context Protocol server that bridges AI tools to Atlassian cloud products.

The server solves the problem of giving AI assistants secure, real-time access to data and workflows across Jira, Confluence, Jira Service Management, Bitbucket, Compass, and Loom. It operates as a cloud-hosted bridge that uses the Teamwork Graph to connect these products, allowing Claude, ChatGPT, Cursor, VS Code, and other AI tools to interact with Atlassian data. Authentication is handled through OAuth 2.1 or API tokens, ensuring secure connections without exposing credentials directly to client applications.

Teams using Atlassian products who want to augment their AI tools with access to project management, documentation, code repositories, and service management data should consider this server. It is particularly suited for organizations already invested in the Atlassian ecosystem and seeking to integrate their existing workflows with AI agents. The tool is officially maintained by Atlassian and is cloud-hosted, meaning users do not need to manage server infrastructure themselves.

The project shows active development with regular updates to support new features and maintain compatibility with evolving AI platforms. The codebase is written in JavaScript and is publicly available for inspection and contribution. The server is registered in the MCP Registry and maintains compatibility with the Model Context Protocol specification, ensuring it works with current and future MCP-compatible clients.