Home / MCP / Better Confluence Communication Server

Better Confluence Communication Server

Implements MCP for Confluence to execute CQL queries and retrieve page content.

typescript

24stars

View on GitHub

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
    "mcpServers": {
        "confluence_mcp": {
            "command": "npx",
            "args": [
                "-y",
                "@zereight/mcp-confluence"
            ],
            "env": {
                "CONFLUENCE_URL": "https://XXXXXXXX.atlassian.net",
                "JIRA_URL": "https://XXXXXXXX.atlassian.net",
                "CONFLUENCE_API_MAIL": "Your email",
                "CONFLUENCE_API_KEY": "KEY_FROM: https://id.atlassian.com/manage-profile/security/api-tokens",
                "CONFLUENCE_IS_CLOUD": "true"
            }
        }
    }
}

You can run a dedicated MCP server that connects to Confluence to execute CQL queries and fetch page content, exposing these capabilities to MCP clients through a standardized protocol. This server streamlines Confluence data access and makes it easy to integrate Confluence content into your MCP-enabled workflows.

How to use

Set up the Confluence MCP server to expose its data sources and actions to MCP clients. You will run the server locally or in your environment, providing your Confluence access details via environment variables. Common tasks include executing CQL searches against Confluence, retrieving page content by ID, and using related Jira tools when needed. The server supports cloud and server/data center Confluence instances and adjusts API endpoints accordingly.

How to install

Prerequisites you need before installing this MCP server are a Node.js runtime and npm (Node Package Manager). Install Node.js from the official source for your operating system; npm is included with Node.js.

Install and run the MCP server using the following command structure. This uses npx to invoke the MCP package directly.

`
{`mcpServers`: {`Confluence communication server`: {`command`: `npx`, `args`: ["-y", "@zereight/mcp-confluence"], `env`: {`CONFLUENCE_URL`: "https://XXXXXXXX.atlassian.net", `JIRA_URL`: "https://XXXXXXXX.atlassian.net", `CONFLUENCE_API_MAIL`: "Your email", `CONFLUENCE_API_KEY`: "KEY_FROM: https://id.atlassian.com/manage-profile/security/api-tokens", `CONFLUENCE_IS_CLOUD`: "true"}}}}
```

This snippet shows the MCP server configuration you will use to start the server. You can adapt the environment values to your Confluence instance.

Additional notes

If you use Cursor, set the environment variables for Confluence access before starting the MCP server. Example usage with Cursor:

```
env [email protected] CONFLUENCE_API_KEY=your-key CONFLUENCE_URL=your-confluence-url JIRA_URL=your-jira-url npx -y @zereight/mcp-confluence
```

Environment variables you may configure include:
- CONFLUENCE_API_MAIL: your Confluence account email
- CONFLUENCE_API_KEY: your Confluence API key
- CONFLUENCE_URL: your Confluence base URL
- JIRA_URL: your Jira base URL
- CONFLUENCE_IS_CLOUD: set to "true" for Cloud, or "false" for Server/Data Center

Note on cloud vs. server differences: Cloud endpoints use /wiki/rest/api, while Server endpoints use /rest/api. Adjust your connections accordingly.

Confluence Tools

The server provides the following actions to work with Confluence data.

Jira Tools

The server also exposes Jira-related actions to interact with Jira data alongside Confluence.

Available tools

execute_cql_search

Executes a CQL query against Confluence to locate pages and related content.

get_page_content

Retrieves the content of a specific Confluence page by its page ID.

create_page

Creates a new Confluence page within a specified space and returns the new page details.

update_page

Updates the content and optionally the title of an existing Confluence page by its ID.

execute_jql_search

Executes a JQL query against Jira to search for issues.

create_jira_issue

Creates a new Jira issue with project, summary, and issue type.