Facebook MCP Server by CData

@CDataSoftware

Basic information

About Facebook MCP Server by CData

This project builds a read-only MCP server. For full read, write, update, delete, and action capabilities and a simplified setup, check out our free CData MCP Server for Facebook (beta): https://www.cdata.com/download/download.aspx?sku=RBZK-V&type=beta

#facebook #mcp-server #cdata

Facebook MCP Server by CData config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "{classname_dash}": {
      "command": "PATH\\TO\\java.exe",
      "args": [
        "-jar",
        "PATH\\TO\\CDataMCP-jar-with-dependencies.jar",
        "PATH\\TO\\facebook.prp"
      ]
    }
  }
}

Facebook MCP Server by CData tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Facebook MCP Server by CData?

Facebook MCP Server by CData is a read-only Model Context Protocol (MCP) server that allows LLMs like Claude Desktop to query live Facebook data. It wraps the CData JDBC Driver for Facebook, which exposes Facebook data as relational SQL models, so users can retrieve live information using natural language without writing SQL.

How to use Facebook MCP Server by CData?

Clone the repository, build the JAR with mvn clean install, download and install the CData JDBC Driver for Facebook, license it, and configure a connection string using the driver’s utility. Create a .prp file with JDBC details (prefix, driver path, JDBC URL, etc.), then add the server to Claude Desktop’s claude_desktop_config.json. Restart the client to see the server. The server uses stdio transport and must run on the same machine as the client.

Key features of Facebook MCP Server by CData

Read-only access to Facebook data via live SQL queries.
Natural language interface – no SQL knowledge required.
Tools: get_tables, get_columns, and run_query (SELECT only).
Built on the CData JDBC Driver for Facebook.
Supports any LLM client that can host MCP servers (e.g., Claude Desktop).
MIT licensed – free to use, modify, and distribute.

Use cases of Facebook MCP Server by CData

Ask an LLM to summarize Facebook page engagement metrics.
Query Facebook ad performance data in real time.
Combine Facebook data with other sources in multi‑tool MCP workflows.
Enable non‑technical users to explore Facebook data via chat.
Provide live business intelligence to AI assistants without custom code.

Frequently asked questions

Is this server read‑only?

Yes. This MCP server provides only read capabilities. For full read, write, update, delete, and action support, CData offers a free beta version of their MCP Server for Facebook.

What are the runtime requirements?

Java (to run the JAR), Maven (to build), and a licensed copy of the CData JDBC Driver for Facebook installed on the same machine.

Where does the data live?

Data is queried live from Facebook through the JDBC driver. No local copy of the data is stored by the server.

What transport or authentication is used?

The server communicates over `stdio`, so it must run on the same host as the client. Authentication uses OAuth, configured through the JDBC connection string builder.

Can I run the server without Claude Desktop?

Yes. Run `java -jar CDataMCP-jar-with-dependencies.jar /path/to/facebook.prp` on its own, but note that `stdio` transport limits it to local‑only clients.

Comments

More Other MCP servers

Klarix Intelligence Engine

Klarix

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.

FastMCP v2 🚀

jlowin

🚀 The fast, Pythonic way to build MCP servers and clients.

26.0K

Maestro

mobile-dev-inc

Painless E2E Automation for Mobile and Web

14.8K

Hindsight

vectorize-io

Hindsight: Agent Memory That Learns

50.4K

Activepieces

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

23.2K