atlassian-confluence — Claude Code MCP server: how to install
Connects AI coding assistants to Confluence spaces to search docs, read attachments, and draft pages. Generated from the OpenAPI specification with automated tool testing.
claude mcp add atlassian-confluence -- uvx mcparmory-atlassian-confluenceWhat atlassian-confluence does
This MCP server exposes Atlassian Confluence API endpoints to AI assistants. It allows your agent to look up team documentation, update existing wiki pages, and upload attachments. Requests pass Pydantic validation before leaving your machine.
Execution requires Python 3.11+ alongside uvx. Built on FastMCP, the standalone package mcparmory-atlassian-confluence handles network resilience with retries and exponential backoff. It supports authentication via Bearer tokens, API keys, or Basic auth.
The server will fail immediately without valid Atlassian credentials in your environment. You can also turn on response sanitization to filter out sensitive corporate fields.
What it helps with
- search internal documentation across Confluence spaces
- publish generated project documentation to wiki pages
- attach logs and architectural files to articles
- update outdated Confluence content directly from the editor
Example prompts for the agent
- Search our Confluence workspace for backend deployment guidelines
- Draft a new Confluence page in the DEV space with our API schema
- Find and inspect the latest attachment on the release notes page
How to install atlassian-confluence
Platform CLI
claude mcp add atlassian-confluence -- uvx mcparmory-atlassian-confluenceuvx runs the command named after the package; if the README names another one, use uvx --from mcparmory-atlassian-confluence <command>
Platform CLI
codex mcp add atlassian-confluence -- uvx mcparmory-atlassian-confluenceuvx runs the command named after the package; if the README names another one, use uvx --from mcparmory-atlassian-confluence <command>
Config file
{
"mcpServers": {
"atlassian-confluence": {
"command": "uvx",
"args": [
"mcparmory-atlassian-confluence"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from mcparmory-atlassian-confluence <command>
Config file
{
"servers": {
"atlassian-confluence": {
"type": "stdio",
"command": "uvx",
"args": [
"mcparmory-atlassian-confluence"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from mcparmory-atlassian-confluence <command>
Platform CLI
gemini mcp add atlassian-confluence uvx mcparmory-atlassian-confluenceuvx runs the command named after the package; if the README names another one, use uvx --from mcparmory-atlassian-confluence <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about atlassian-confluence
How to install atlassian-confluence in Claude Code?
Run claude mcp add atlassian-confluence -- uvx mcparmory-atlassian-confluence in your terminal.
What does atlassian-confluence do?
It connects coding agents to the Confluence API for searching, drafting, and organizing wiki pages and attachments.
Which runtime environment is required?
It runs on Python 3.11 or higher and can be launched directly using the uvx package runner.
