home / mcp / facebook mcp server

Facebook MCP Server

This read-only MCP Server allows you to connect to Facebook 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/).

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

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

You can run a local, read-only MCP server that exposes live Facebook data through the CData JDBC Driver. This server lets you ask natural language questions and receive live data results without writing SQL, while running on your own machine for quick testing and integration with MCP-enabled clients.

How to use

After you start the MCP server, connect your MCP client to the local stdio server on the same machine. You will interact with Facebook data through built-in tools that let you discover data structures, run queries, and retrieve results in a conversational way. You can ask questions like what is the open opportunities by industry, how many tickets are open in a project, or what calendar events you have today. The server handles the data access under the hood, so you don’t need to write SQL.

How to install

Prerequisites you need before installing: a Java Development Kit (JDK) and Maven for building the MCP server. Ensure you have a working Java environment and Maven installed on your operating system.

1) Clone the MCP server project and enter the directory.

git clone https://github.com/cdatasoftware/facebook-mcp-server-by-cdata.git
cd facebook-mcp-server-by-cdata

2) Build the server to produce the MCP JAR with dependencies.

mvn clean install

3) Download and install the CData JDBC Driver for Facebook from the official site. You will need this driver to connect to Facebook data.

4) License the CData JDBC Driver. Open your driver installation folder and run the license command, then provide your name, email, and a license key or TRIAL key as prompted.

5) Configure the JDBC connection to Facebook. Use the Driver’s connection utility to test the connection and copy the resulting connection string for later use in the .prp file.

6) Create a .prp file for your JDBC connection (example name: facebook.prp) with the required properties like Prefix, ServerName, ServerVersion, DriverPath, DriverClass, and JdbcUrl, and leave Tables blank to access all data or specify a subset.

7) Prepare your MCP startup command by pointing to the .prp file you created.

8) You are ready to start the MCP server using the stdio configuration described below.

Additional configuration and start details

To run the MCP server on its own using stdio, start the server with the following command. This will load your facebook.prp file and expose the Facebook data through the MCP interface.

java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/facebook.prp

Notes on usage with Claude Desktop or other MCP clients

Install and configure your MCP client to recognize the local stdio server. After starting the server, refresh the client so the MCP server appears in the list, then you can start querying the data sources using natural language without writing SQL. If the client does not detect the server immediately, fully quit the client and relaunch it.

Configuration and troubleshooting

Ensure your Java runtime is available and that you started the server with the correct path to facebook.prp. If you cannot see the MCP server in your client, quit the client entirely and reopen it so it detects newly started servers. If data retrieval fails, verify that the JDBC Driver is correctly licensed and that the connection string in your facebook.prp is valid. If issues persist, contact CData Support or join the CData Community for guidance.

Tools and capabilities you gain

The MCP server provides common data access tools that let you discover tables, inspect columns, and run select queries against your Facebook data. In practice, you will use these tools to explore the data model and then pose natural language questions to retrieve insights.

Troubleshooting quick start

If you cannot see the MCP Server in your client or cannot retrieve data, ensure you have fully quit and restarted the MCP client after starting the server. Double-check the .prp connection string and the path to the JDBC driver. For further help, consult the CData Community.

Available tools

facebook_get_tables

Retrieves a list of tables available in the data source. The output is in CSV with column headers.

facebook_get_columns

Retrieves a list of columns for a specified table. The output is in CSV with column headers.

facebook_run_query

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