Confluence Communication Server MCP Server

Knowledge & MemoryTypeScript

Interact with Atlassian Confluence pages and content

Available Tools

execute_cql_search

Run a CQL query to search for Confluence pages

cqllimit

get_page_content

Fetch the content of a Confluence page

pageId

update_page_content

Update the content of a Confluence page

pageIdcontenttitle

The Confluence Communication Server provides a seamless interface for AI assistants to interact with Atlassian Confluence workspaces. It enables searching through pages using CQL queries, retrieving page content, and updating existing pages directly from AI interactions. This TypeScript-based server bridges the gap between AI assistants and your organization's knowledge base stored in Confluence. It allows for both reading and writing operations, making it possible to not only reference existing documentation but also contribute to it.

Overview

The Confluence Communication Server allows AI assistants to interact with your Atlassian Confluence workspace. This server provides tools for searching, reading, and updating Confluence pages, making your organization's knowledge base accessible to AI assistants.

Installation

Prerequisites

Node.js installed on your system
Atlassian Confluence account with API access
API token from Atlassian (generate at https://id.atlassian.com/manage-profile/security/api-tokens)

Installation Steps

Install the server using Smithery (recommended):

npx -y @smithery/cli install @KS-GEN-AI/confluence-mcp-server --client claude

Alternatively, you can clone the repository and build it manually:

git clone https://github.com/KS-GEN-AI/confluence-mcp-server.git
cd confluence-mcp-server
npm install
npm run build

Configuration

To use the server with Claude Desktop or other compatible clients, you need to add the server configuration to your client's config file:

For MacOS: Edit ~/Library/Application Support/Claude/claude_desktop_config.json For Windows: Edit %LOCALAPPDATA%/Claude/claude_desktop_config.json

Add the following configuration, replacing the placeholder values with your actual Confluence credentials:

{
  "mcpServers": {
    "Confluence communication server": {
      "command": "node",
      "args": ["/PATH_TO_THE_PROJECT/build/index.js"],
      "env": {
        "CONFLUENCE_URL": "https://YOUR_WORKSPACE.atlassian.net/wiki",
        "CONFLUENCE_API_MAIL": "your.email@example.com",
        "CONFLUENCE_API_KEY": "YOUR_ATLASSIAN_API_TOKEN"
      }
    }
  }
}

Usage

Once installed and configured, the Confluence Communication Server will be available to your AI assistant. You can ask the assistant to:

Search for pages in your Confluence workspace using CQL queries
Retrieve the content of specific Confluence pages
Update the content of existing Confluence pages

Example Prompts

"Search for all Confluence pages related to our product roadmap"
"Get the content of the Engineering Onboarding page"
"Update our meeting notes page with today's discussion summary"

Troubleshooting

If you encounter issues with the server:

Verify your Confluence credentials are correct
Check that your API token has the necessary permissions
Ensure the path to the build/index.js file is correct in your configuration

For more advanced debugging, you can use the MCP Inspector:

npm run inspector

This will provide a URL to access debugging tools in your browser, which can help identify communication issues between the AI assistant and the Confluence server.