confluence

This MCP server provides a Python-based Confluence integration exposed via the MCP protocol. It exposes tools to search content, list spaces, and perform CRUD operations on Confluence pages through a standardized tool interface. You can query Confluence with the search_confluence tool, retrieve available spaces with get_spaces, fetch page content with get_page_content, and create, update, or delete pages using create_page, update_page, and delete_page respectively. The server is designed to run in a Flask environment and is suitable for deployment on Cloud Run or similar platforms. Before usage, configure your Confluence instance URL and an access token via environment variables so the server can authenticate with Confluence on behalf of your agent.

To use the tools, authenticate with your Confluence instance by setting CONFLUENCE_URL and CONFLUENCE_ACCESS_TOKEN in your environment. Then you can call the tools from your agent as described in the README, for example: search_confluence("type=page AND text ~ 'MCP'"), get_spaces(), get_page_content(space_key, page_id), create_page(space_key, title, content). The tools return structured dictionaries containing data or error information, enabling your agent to compose responses and iterate on content within Confluence.

Prerequisites:

• Python 3.8+ installed on your system
• Git to clone the repository
• Access token for Confluence Cloud (or on-prem) with appropriate permissions

Installation steps:

1. Clone the repository git clone https://github.com/pawankumar94-confluence-mcp-server.git cd confluence-mcp-server

2. Create and activate a virtual environment (optional but recommended) python -m venv venv source venv/bin/activate # on Windows use venv\Scripts\activate

3. Install dependencies pip install -r requirements.txt

4. Configure environment variables (see .env guidance in README)

   • Create a .env file in the project root with: CONFLUENCE_URL=https://your-instance.atlassian.net/wiki CONFLUENCE_ACCESS_TOKEN=your_access_token PORT=8080 # optional

5. Run the server locally python example.py

6. Optional: prepare for Cloud Run or container deployment following the README's Cloud Run steps

Tips and common issues:

• Ensure your Confluence access token has the necessary permissions for the actions you plan to perform (read/write/delete).
• Store sensitive tokens in a secure environment (Cloud Run secrets or similar) rather than hard-coding.
• If you encounter authentication errors, verify the CONFLUENCE_URL and token scope, and ensure your token is active.
• The PORT value is optional; if not set, the server defaults to 8080.
• For Cloud Run deployment, ensure the container exposes port 8080 and that the environment variables are passed to the container.
• The MCP tool interface returns either data or an error object like {"error": "message"}; handle errors gracefully in your agent.