MCP Atlassian
# MCP Atlassian



[](https://github.com/sooperset/mcp-atlassian/actions/workflows/tests.yml)

[](https://mcp-atlassian.soomiles.com)
Model Context Protocol (MCP) server for Atlassian products (Confluence and Jira). Supports both Cloud and Server/Data Center deployments.
https://github.com/user-attachments/assets/35303504-14c6-4ae4-913b-7c25ea511c3e
<details>
<summary>Confluence Demo</summary>
https://github.com/user-attachments/assets/7fe9c488-ad0c-4876-9b54-120b666bb785
</details>
## Quick Start
### 1. Get Your API Token
Go to https://id.atlassian.com/manage-profile/security/api-tokens and create a token.
> For Server/Data Center, use a Personal Access Token instead. See [Authentication](https://mcp-atlassian.soomiles.com/docs/authentication).
### 2. Configure Your IDE
Add to your Claude Desktop or Cursor MCP configuration:
```json
{
"mcpServers": {
"mcp-atlassian": {
"command": "uvx",
"args": ["mcp-atlassian"],
"env": {
"JIRA_URL": "https://your-company.atlassian.net",
"JIRA_USERNAME": "your.email@company.com",
"JIRA_API_TOKEN": "your_api_token",
"CONFLUENCE_URL": "https://your-company.atlassian.net/wiki",
"CONFLUENCE_USERNAME": "your.email@company.com",
"CONFLUENCE_API_TOKEN": "your_api_token"
}
}
}
}
```
> **Server/Data Center users**: Use `JIRA_PERSONAL_TOKEN` (or `JIRA_USERNAME` + `JIRA_PASSWORD`), and `CONFLUENCE_PERSONAL_TOKEN` (or `CONFLUENCE_USERNAME` + `CONFLUENCE_PASSWORD`). See [Authentication](https://mcp-atlassian.soomiles.com/docs/authentication) for details.
#### Autohand Code
Use the same `uvx` server with your Atlassian credentials:
```bash
autohand mcp add mcp-atlassian env \
JIRA_URL=https://your-company.atlassian.net \
JIRA_USERNAME=your.email@company.com \
JIRA_API_TOKEN=your_api_token \
CONFLUENCE_URL=https://your-company.atlassian.net/wiki \
CONFLUENCE_USERNAME=your.email@company.com \
CONFLUENCE_API_TOKEN=your_api_token \
uvx mcp-atlassian
```
Add `--scope project` after `add` to keep the configuration in the current
project. See [Autohand Code](https://github.com/autohandai/code-cli/) for current
installation and CLI details.
### 3. Start Using
Ask your AI assistant to:
- **"Find issues assigned to me in PROJ project"**
- **"Search Confluence for onboarding docs"**
- **"Create a bug ticket for the login issue"**
- **"Update the status of PROJ-123 to Done"**
## Documentation
Full documentation is available at **[mcp-atlassian.soomiles.com](https://mcp-atlassian.soomiles.com)**.
Documentation is also available in [llms.txt format](https://llmstxt.org/), which LLMs can consume easily:
- [`llms.txt`](https://mcp-atlassian.soomiles.com/llms.txt) — documentation sitemap
- [`llms-full.txt`](https://mcp-atlassian.soomiles.com/llms-full.txt) — complete documentation
| Topic | Description |
|-------|-------------|
| [Installation](https://mcp-atlassian.soomiles.com/docs/installation) | uvx, Docker, pip, from source |
| [Authentication](https://mcp-atlassian.soomiles.com/docs/authentication) | API tokens, PAT, OAuth 2.0 |
| [Configuration](https://mcp-atlassian.soomiles.com/docs/configuration) | IDE setup, environment variables |
| [HTTP Transport](https://mcp-atlassian.soomiles.com/docs/http-transport) | SSE, streamable-http, multi-user |
| [Tools Reference](https://mcp-atlassian.soomiles.com/docs/tools-reference) | All Jira & Confluence tools |
| [Troubleshooting](https://mcp-atlassian.soomiles.com/docs/troubleshooting) | Common issues & debugging |
## Compatibility
| Product | Deployment | Support |
|---------|------------|---------|
| Confluence | Cloud | Fully supported |
| Confluence | Server/Data Center | Supported (v6.0+) |
| Jira | Cloud | Fully supported |
| Jira | Server/Data Center | Supported (v8.14+) |
## Key Tools
| Jira | Confluence |
|------|------------|
| `jira_search` - Search with JQL | `confluence_search` - Search with CQL |
| `jira_get_issue` - Get issue details | `confluence_get_page` - Get page content |
| `jira_create_issue` - Create issues | `confluence_create_page` - Create pages |
| `jira_update_issue` - Update issues | `confluence_update_page` - Update pages |
| `jira_transition_issue` - Change status | `confluence_add_comment` - Add comments |
**98 tools total** — See [Tools Reference](https://mcp-atlassian.soomiles.com/docs/tools-reference) for the complete list.
## Agent Skills
Pre-configured workflows and skill packages for AI assistants (Antigravity, Claude, Cursor):
| Skill | Description | Location |
|-------|-------------|----------|
| `generate-status-report` | Summarizes Jira sprint metrics and Confluence updates. | [`skills/generate-status-report`](skills/generate-status-report/SKILL.md) |
| `capture-tasks-from-meeting-notes` | Parses action items from meeting notes to draft Jira issues. | [`skills/capture-tasks-from-meeting-notes`](skills/capture-tasks-from-meeting-notes/SKILL.md) |
| `triage-issue` | Classifies Jira issues, suggests priority/components/labels, and flags duplicates. | [`skills/triage-issue`](skills/triage-issue/SKILL.md) |
## Security
Never share API tokens. Keep `.env` files secure. See [SECURITY.md](SECURITY.md).
## Contributing
See [CONTRIBUTING.md](CONTRIBUTING.md) for development setup.
## License
MIT - See [LICENSE](LICENSE). Not an official Atlassian product.
TDQS
Scored across 98 tools
Most tools follow a clear resource+action pattern, but there are genuine overlaps: jira_update_issue can transition, comment, and log work alongside dedicated jira_transition_issue, jira_add_comment, and jira_add_worklog tools; jira_get_issue_dates and jira_get_issue_sla both analyze status/time; and multiple issue-listing variants (project, board, sprint, queue, JQL) require careful selection. The descriptions do a good job of clarifying scope, so the ambiguity is manageable but not eliminated.
All tools consistently use snake_case with jira_/confluence_ prefixes and a clear verb_noun structure: get_, create_, update_, delete_, add_, remove_, search_. Batch variants follow the same pattern (batch_create, batch_get, upload_attachments), making the naming highly predictable across 98 tools.
98 tools is far beyond even the 50+ extreme-mismatch threshold. While the server legitimately spans both Jira and Confluence with many subdomains, the sheer surface area creates a heavy navigation burden for agents and could benefit from consolidation or modular sub-servers.
The toolset provides remarkably comprehensive coverage: Jira issues, transitions, comments, worklogs, watchers, links, attachments, sprints, versions, projects, fields, forms, SLA/dev info, and Confluence pages, comments, labels, restrictions, permissions, attachments, templates, and history/diff. Minor gaps such as no Jira delete-comment, no Confluence delete-comment, and no remove-remote-link keep it from a 5, but agents can generally work around these.