Our take
Activeregular commits and releases- Activity
- 71
- Community
- 70
- Issues
- 74
- Pull requests
- 75
+67 stars in the last 18 days
- Releases more often than 78% of the projects we track
- More contributors than 78% of the projects we track
- Merges more pull requests than 78% of the projects we track
This is an actively maintained Python MCP integration for teams that want practical Jira and Confluence actions available to their AI assistants.
Good fit if
- Your team uses Jira or Confluence and wants an MCP-compatible assistant to search or modify that content.
- You can provide the appropriate Atlassian credentials and configure a Python 3.10-or-newer runtime, or use Docker.
- You value an actively developed project, with recent commits and releases and issue reports typically handled within days.
Look elsewhere if
- You need an integration for Atlassian products other than Jira and Confluence.
- Your deployment is an older Server/Data Center version than the documented support minimums.
- Your assistant client cannot use MCP servers or your organization cannot permit the required Atlassian credentials.
All health signals
| Last commit | 2026-09-19 (22 days ago) |
|---|---|
| Commits, last 90 days | 59 |
| Releases, last 12 months | 25 (latest v0.23.1, 2026-08-19) |
| Contributors | 100+ (top contributor: 70% of commits) |
| Issues closed, last 90 days | 35+ (typically closed in 3 days) |
| Pull requests merged, last 90 days | 58 (typically merged in 0 days) |
| Project age | 23 months |
Checked on 2026-10-12 with the GitHub API.
Overview
mcp-atlassian connects MCP-compatible AI assistants to Jira and Confluence. It exposes Atlassian operations as tools, so an assistant can search issues and pages, create or update content, and perform other supported actions without requiring users to switch between the assistant and Atlassian interfaces.
It supports Cloud as well as specified Server/Data Center versions. This makes it relevant to teams that want assistant-driven access to existing Atlassian workspaces, provided they can configure the required credentials and deployment settings.
Key Features
- Provides Jira tools for JQL searches, issue retrieval and creation, updates, and status transitions.
- Provides Confluence tools for CQL searches, page retrieval and creation, updates, and comments.
- Supports Atlassian Cloud and Server/Data Center deployments, with product-specific minimum versions documented for the latter.
- Offers authentication options including API tokens, personal access tokens, and OAuth 2.0, according to its documentation.
- Can be run through
uvx, Docker, pip, or from source. - Documents stdio and HTTP transports, including SSE and streamable HTTP.
Use Cases
- A Jira user can ask an MCP-compatible assistant to find assigned issues or change an issue’s status during project work.
- A support or engineering team can create and update Jira tickets from an assistant conversation when triaging reported bugs.
- Staff can search Confluence for onboarding or process documentation without manually navigating the wiki.
- Teams operating Jira or Confluence Server/Data Center can connect those deployments to an assistant when they meet the documented version requirements.
What you need
Detected in the repository
- Python >=3.10 (from pyproject.toml)
- A Dockerfile, so it can run in a container
- A Helm chart for Kubernetes
- A test suite and automated checks on GitHub Actions
License in plain words
MITpermissive
- Commercial use: yes
- Modify and redistribute: yes
- You must keep: the copyright and license notice
- Share your changes: no
A summary, not legal advice: the LICENSE file is what applies.
Getting Started
Install and run with uvx mcp-atlassian, then configure your MCP client with the Jira or Confluence URL and credentials. See the README for configuration examples and deployment details.
Considerations
The server can create and update Atlassian content as well as read it, so credential handling and the permissions granted to its Atlassian account matter. Follow the project’s security guidance and avoid exposing tokens in shared configuration. The repository has a substantial number of open issues, although its recent activity indicates ongoing maintenance and relatively prompt issue handling. Server/Data Center support has minimum versions, so verify compatibility before rollout.
Found this useful?
Share it with someone who would like mcp-atlassian.