Confluence Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Confluence Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Fast, surgical Confluence MCP server for AI agents.
Unlike generic Atlassian MCP servers, this one is Confluence-only and optimized for how AI agents actually work with documentation:
uvx --from git+https://github.com/1vecera/confluence-mcp confluence-mcppip install git+https://github.com/1vecera/confluence-mcpSet these environment variables:
CONFLUENCE_URL=https://yoursite.atlassian.net
[email protected]
CONFLUENCE_API_TOKEN=your-api-tokenGet your API token at: https://id.atlassian.com/manage-profile/security/api-tokens
Add to ~/.claude.json:
{
"mcpServers": {
"confluence": {
"command": "uvx",
"args": ["--from", "git+https://github.com/1vecera/confluence-mcp", "confluence-mcp"],
"env": {
"CONFLUENCE_URL": "https://yoursite.atlassian.net",
"CONFLUENCE_USERNAME": "[email protected]",
"CONFLUENCE_API_TOKEN": "your-token"
}
}
}
}| Tool | Description |
|---|---|
get_page | Get page content in markdown or storage format |
get_page_tree | Download entire page hierarchy at once |
get_page_sections | List all sections with their content |
get_section | Get a specific section by heading name |
search_pages | Search via CQL or simple text |
list_page_images | List all image references in a page |
| Tool | Description |
|---|---|
update_page | Update entire page content |
update_section | Replace only a specific section — the key surgical edit tool |
append_to_section | Add content to end of a section |
find_replace_in_page | Find and replace text preserving HTML |
create_page | Create a new page |
| Tool | Description |
|---|---|
list_attachments | List all attachments on a page |
download_attachment | Download an attachment by filename |
upload_attachment | Upload a file attachment |
upload_image_and_embed | Upload image + optionally rewrite page to embed it |
| Tool | Description |
|---|---|
get_labels | Get labels on a page |
add_label | Add a label to a page |
Instead of downloading and re-uploading an entire page:
update_section(page_id="123456", heading="Status", new_content="Project is **on track** for Q2 delivery.")get_page_tree(page_id="123456", include_body=True)upload_image_and_embed(page_id="123456", filename="arch.png", image_base64="...", replace_url="https://old-host.com/arch.png")uv sync --extra dev
uv run pytest --cov=confluence_mcp --cov-report=term-missingMIT
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.