Frequently Asked Questions (FAQ) about CData MCP Server for Neo4J

Q: What is the CData MCP Server for Neo4J?

A: The CData MCP Server for Neo4J is a read-only server that allows Large Language Models (LLMs) like Claude Desktop to query live data from Neo4J graph databases using natural language. It acts as a bridge between Neo4J and LLMs, leveraging the CData JDBC Driver for Neo4J.

Q: What is MCP (Model Context Protocol)?

A: MCP is an open protocol that standardizes how applications provide context to LLMs, enabling them to access and interact with external data sources and tools.

Q: What are the benefits of using the CData MCP Server for Neo4J?

A: Key benefits include seamless integration with Claude Desktop, natural language querying of Neo4J data, simplified access through the MCP interface, and the ability to empower AI agents with real-time insights from your graph database.

Q: What data sources are supported by CData MCP Server?

A: CData MCP Server supports more than 200+ data sources (Access, Act CRM, Google Analytics, etc).

Q: How do I set up the CData MCP Server for Neo4J?

A: The setup process involves cloning the repository, building the server, downloading and licensing the CData JDBC Driver for Neo4J, configuring the connection, creating a .prp file, and configuring Claude Desktop to recognize the new server.

Q: Is the CData MCP Server for Neo4J read-only?

A: Yes, this specific server is designed for read-only access to ensure data integrity. CData also offers a read/write beta version.

Q: What is the CData JDBC Driver for Neo4J?

A: The CData JDBC Driver for Neo4J connects to Neo4J databases and exposes them as relational SQL models, making them accessible to applications that support JDBC.

Q: How do I license the CData JDBC Driver for Neo4J?

A: Navigate to the lib folder in the driver’s installation directory and run the command java -jar cdata.jdbc.neo4j.jar --license. Enter your name, email, and license key (or “TRIAL” for a trial license).

Q: How do I configure the connection to my Neo4J data source?

A: Use the Connection String utility (java -jar cdata.jdbc.neo4j.jar) to configure the connection string. Test the connection and copy the connection string for use in your .prp file.

Q: What is a .prp file and how do I create one?

A: A .prp file stores JDBC connection properties such as Prefix, ServerName, DriverPath, DriverClass, JdbcUrl, and Tables. Create a text file with these properties and save it with the .prp extension.

Q: How do I configure Claude Desktop to use the CData MCP Server for Neo4J?

A: Add an entry to the mcpServers section of the claude_desktop_config.json file, specifying the command and arguments to run the MCP server.

Q: What are the available tools in the CData MCP Server for Neo4J?

A: The available tools include {servername}_get_tables, {servername}_get_columns, and {servername}_run_query, which allow you to retrieve table lists, column lists, and execute SQL queries, respectively.

Q: How do I use the tools in the CData MCP Server for Neo4J?

A: These tools can be accessed through JSON-RPC requests. Refer to the JSON-RPC Request Examples in the documentation for details.

Q: What do I do if I cannot see my CData MCP Server in Claude Desktop?

A: Ensure that you have fully quit and restarted Claude Desktop after configuring the server.

Q: What do I do if Claude Desktop is unable to retrieve data?

A: Verify that you have configured your connection properly. Use the Connection String builder to create the connection string and copy it into the .prp file.

Q: Where can I get help if I have trouble connecting to my data source?

A: Contact the CData Support Team for assistance with data source connectivity.

Q: Where can I get help if I have trouble using the MCP server?

A: Join the CData Community for troubleshooting tips and solutions.

Q: What is the license for the CData MCP Server for Neo4J?

A: The MCP server is licensed under the MIT License, allowing for free use, modification, and distribution.

Q: How does UBOS relate to the CData MCP Server for Neo4J?

A: UBOS is a full-stack AI Agent Development Platform that complements the CData MCP Server by providing a centralized platform for managing AI agents, simplifying data connectivity, enabling custom AI agent development, and ensuring scalability.