mcp-confluence-server

Purpose

mcp-confluence-server is a Model Context Protocol (MCP) server designed to enable interaction with Confluence through the Confluence Data Center REST API. It enables AI models to operate Confluence content through natural language, such as searching, reading, creating, updating, and deleting pages.

Main Capabilities

The server provides the following operation tools:

• execute_cql_search: Execute a CQL (Confluence Query Language) query to search for pages. Parameters: cql (CQL query string), limit (number of results to return, default 10).
• get_page_content: Get the content of a Confluence page by page ID. Parameters: pageId (Confluence page ID).
• get_page_with_body: Get a page and its body content.
• find_pages_by_space: Find pages by space key. Parameters: spaceKey (Confluence space key), limit (maximum number of results to return, default 10), expand (optional comma-separated list of properties).
• find_page_by_title: Find a page by title and space key. Parameters: title (page title).
• create_page: Create a new page in Confluence. Parameters: content (page content in storage format, HTML), parentId (optional parent page ID).
• update_page: Update an existing page in Confluence. Parameters: content (new page content, storage format HTML), title (optional new title), spaceKey (optional space key, only needed when changing spaces).
• delete_page: Delete a page by ID.

Usage

Installation

1. Clone the repository:git clone <repository-url>
2. Install dependencies.
3. In the project root directory, create the .env file containing the necessary variables (values need to be adjusted according to the Confluence instance).

Running the Server

Development mode (recommended): Use the MCP CLI tool to run in development mode, which starts the MCP Inspector UI for testing and debugging the server. By default, MCP Inspector will start at http://127.0.0.1:6274 .

Direct execution (not recommended): Although the script can be executed directly with Python, this is not the standard way to run an MCP server, has limited functionality, and is only for basic testing.

Installing in Claude Desktop

The server can be installed in Claude Desktop for use.

Applicable Scenarios

• Query and operate Confluence content through natural language, such as "find all pages in the DOCS space", "get the content of the page with ID 123456", "create a new page titled 'Meeting Notes' in the TEAM space with the content 'Meeting notes'", "update the content of the page with ID 123456 to 'Updated meeting notes'", "update the title of page 123456 to 'Revised meeting notes'".

Limitations

• Functionality is limited when executed directly with Python and is only for testing.
• Requires correct configuration of the .env file to connect to the Confluence instance.
• Information about authentication methods, specific dependency installation commands, and detailed Claude Desktop installation steps is currently not provided.