Confluence

This read-only MCP Server allows you to connect to Confluence data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out the first managed MCP platform: CData Connect AI (https://www.cdata.com/ai/).

java

GitHub Stars

java

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "cdatasoftware-confluence-mcp-server-by-cdata": {
      "command": "java",
      "args": [
        "-jar",
        "CDataMCP-jar-with-dependencies.jar",
        "/PATH/TO/confluence.prp"
      ]
    }
  }
}

You can query live Confluence data from Claude Desktop or other MCP clients using a local, read-only MCP server. This server wraps the CData JDBC Driver for Confluence and exposes data through a simple MCP interface so you can ask natural-language questions and retrieve up-to-date information without writing SQL.

How to use

Once you have the MCP server running, you interact with it through your MCP client. The client discovers the Confluence MCP server as a data source and provides built-in tools to read data. You can ask questions like “What is the total number of open tickets in the SUPPORT project?” or “What is the correlation between closed won opportunities and account industry?” The client handles translating your natural-language questions into queries against Confluence data via the MCP server.

To use the server effectively, ensure your client is configured to connect to the local MCP server instance. Since this setup is designed for local, read-only access, you can query current Confluence data without writing any SQL. If you need to verify what data is exposed, you can use the provided tools to list tables and columns, then run safe read-only queries to answer your questions.

How to install

Prerequisites you need before installation: Java Runtime Environment (JRE) for running the MCP server, and Maven for building the server JAR.

# 1) Clone the project
git clone https://github.com/cdatasoftware/confluence-mcp-server-by-cdata.git
cd confluence-mcp-server-by-cdata

# 2) Build the server JAR with dependencies
mvn clean install

# This creates the JAR file: CDataMCP-jar-with-dependencies.jar

Install and license the CData JDBC Driver for Confluence (required to connect to Confluence data). Follow the driver installation instructions from the CData site and license it as part of setup.
Prepare a JDBC connection file (confluence.prp) with your connection details. This file will be used by the MCP server to connect to Confluence.
Run the MCP server locally using the prepared prp file. The server runs on stdio, so you launch it on the same machine as your client.

# 6) Start the MCP server (stdio) with the prepared property file
java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/confluence.prp

Configuration and runtime details

The MCP server is started with a single command that invokes Java to run the MCP launcher JAR, followed by the path to your configuration file. The configuration file describes your JDBC driver, the JDBC URL, and which tables to expose. A typical setup begins by licensing the driver, configuring the connection, and then starting the MCP server with the prepared .prp file.

Troubleshooting and tips

If you cannot see the MCP server in your client, ensure you have fully quit the client and then restart it so the new server is discovered. If data cannot be retrieved, verify that the connection string in confluence.prp is correct and test the connection using the Driver’s connection utilities. If you encounter further issues, verify the MCP server process is running on the expected machine and that the client can access it via the local environment.

Tools and capabilities

The MCP server exposes tooling to interact with Confluence data in read-only form. Core tools include the ability to list available tables, list columns for a table, and execute read-only queries against the data source.

Available tools

confluence_get_tables

Retrieves a list of tables available in the Confluence data source. The output is in CSV format with a header row.

confluence_get_columns

Retrieves a list of columns for a specified table. The output is in CSV format with a header row.

confluence_run_query

Executes a SQL SELECT query against the Confluence data source and returns the results.

Built by

VeilStrat

AI signals for GTM teams