Confluence MCP Server by CData

What is Confluence MCP Server by CData?

A read-only MCP server that allows LLMs (like Claude Desktop) to query live Confluence data using natural language. It is built on the CData JDBC Driver for Confluence, which exposes Confluence as relational SQL models. This server wraps that driver and makes Confluence data available through a simple MCP interface — no SQL required.

How to use Confluence MCP Server by CData?

Clone the repository, build the JAR with mvn clean install, download and license the CData JDBC Driver for Confluence, create a .prp file with your JDBC connection details, then add the MCP server entry to your client’s configuration (e.g., claude_desktop_config.json). The server runs via stdio and must be on the same machine as the client.

Key features of Confluence MCP Server by CData

• Read-only access to live Confluence data
• Natural language querying via LLM clients
• Built on the CData JDBC Driver for Confluence
• Tools: {prefix}_get_tables, {prefix}_get_columns, {prefix}_run_query
• Output returned in CSV format
• Uses stdio transport

Use cases of Confluence MCP Server by CData

• Ask LLM clients “How many open pages in the SUPPORT space?”
• Retrieve live information from Confluence without writing SQL
• Discover available tables and columns in your Confluence instance
• Combine Confluence data with other CData‑connected sources in multi‑server setups

FAQ from Confluence MCP Server by CData

Is this server read-only?

Yes. This server only supports read operations. For full CRUD capabilities, use the free CData MCP Server for Confluence (beta) linked in the README.

What are the runtime requirements?

Java (the MCP server JAR), the CData JDBC Driver for Confluence (must be separately downloaded and licensed), and Maven to build the server. The client (e.g., Claude Desktop) must run on the same machine because the transport is stdio.

Where does data live?

Data remains in Confluence. The JDBC driver connects to Confluence over the network; the MCP server never stores or caches data locally.

How are credentials handled?

Authentication is configured in the JDBC connection string (e.g., OAuth). The server passes the connection string to the driver, and OAuth flows open a browser for authentication if needed.

What transport does the server use?

stdio — the server communicates via standard in/out with the MCP client, so both processes must run on the same machine.