- Python 99.4%
- Shell 0.5%
* feat(confluence): add confluence_update_page_section tool for lossless partial updates Adds a new MCP tool and backing PagesMixin method that replaces the content of a single named section without touching the rest of the page. The existing update_page flow converts the full page to Markdown and back, which destroys macros (TOC, Page Properties, Status, etc.), multi-column layouts, and user mentions. This new tool avoids that entirely: 1. Fetch raw Confluence storage XML (no Markdown conversion). 2. Locate the target section by heading text using BeautifulSoup. 3. Replace only the nodes between that heading and the next same-or-higher level heading; everything else — macros, layouts, mentions — is untouched. 4. Write the modified storage XML back with content_representation=storage. New surface area: - PagesMixin.update_page_section() in confluence/pages.py - confluence_update_page_section MCP tool in servers/confluence.py - 6 unit tests covering section replacement, boundary detection, macro preservation, error cases, and format handling Fixes: lossy full-page Markdown round-trip destroying Confluence macros Related: #842 (mentions lost), community report on macro loss * fix(confluence): fix CI failures in update_page_section - Update hardcoded Confluence tool count from 24 to 25 - Replace BeautifulSoup DOM node-move approach with string-splice insertion to avoid PageElement.__copy__ type error flagged by mypy - Run ruff format on changed files * style: apply ruff-format to servers/confluence.py and test_pages.py * docs: document confluence_update_page_section tool - Add Update Page Section section to confluence-pages.mdx with full parameter table, example, tip, and warning about heading matching - Add confluence_update_page_section to confluence_pages toolset list in tools-reference.mdx - Update tool count from 72 to 73 * refactor(confluence): address self-review findings in update_page_section - Fix list[Tag] type annotation: NavigableString siblings are also collected, so broaden to list to avoid a silent lie + type: ignore - Remove stale '# 5. (old nodes removed in step 6 below)' comment - Use heading_text.strip() in 'not found' error to match comparison - Clarify the heading_pos == -1 guard comment: it is unreachable in normal use and indicates a BS4 serialisation edge case, not user error * test(confluence): verify page section updates Add server-level and e2e coverage for the Confluence page section update tool, and align tool count documentation with the registered tools. Github-PR:#1141 --------- Co-authored-by: mcp-maintainer-worker <worker@maintainer.local> |
||
|---|---|---|
| .claude | ||
| .devcontainer | ||
| .github | ||
| docs | ||
| helm | ||
| scripts | ||
| src/mcp_atlassian | ||
| tests | ||
| .dockerignore | ||
| .env.example | ||
| .gitignore | ||
| .mintignore | ||
| .pre-commit-config.yaml | ||
| .worktreeinclude | ||
| AGENTS.md | ||
| CLAUDE.md | ||
| CONTRIBUTING.md | ||
| Dockerfile | ||
| docs.json | ||
| LICENSE | ||
| pyproject.toml | ||
| README.md | ||
| SECURITY.md | ||
| smithery.yaml | ||
| uv.lock | ||
MCP Atlassian
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
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.
2. Configure Your IDE
Add to your Claude Desktop or Cursor MCP configuration:
{
"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_TOKENinstead ofJIRA_USERNAME+JIRA_API_TOKEN. See Authentication for 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.
Documentation is also available in llms.txt format, which LLMs can consume easily:
llms.txt— documentation sitemapllms-full.txt— complete documentation
| Topic | Description |
|---|---|
| Installation | uvx, Docker, pip, from source |
| Authentication | API tokens, PAT, OAuth 2.0 |
| Configuration | IDE setup, environment variables |
| HTTP Transport | SSE, streamable-http, multi-user |
| Tools Reference | All Jira & Confluence tools |
| 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 |
77 tools total — See Tools Reference for the complete list.
Security
Never share API tokens. Keep .env files secure. See SECURITY.md.
Contributing
See CONTRIBUTING.md for development setup.
License
MIT - See LICENSE. Not an official Atlassian product.