Frequently Asked Questions (FAQ) about the HubSpot MCP Server

Q: What is an MCP Server? A: MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to LLMs. An MCP Server acts as a bridge, allowing AI models like Claude to access and interact with external data sources and tools.

Q: What is the HubSpot MCP Server? A: The HubSpot MCP Server by CData is a read-only MCP server that allows you to connect to your HubSpot data from Claude Desktop through CData JDBC Drivers. This enables you to query your HubSpot data using natural language through Claude.

Q: What is CData JDBC Driver? A: CData JDBC Driver connects to various data sources, including HubSpot, by exposing them as relational SQL models. This allows you to interact with your data using SQL queries.

Q: What are the benefits of using the HubSpot MCP Server? A: Benefits include:

• Seamless integration with Claude Desktop.
• Real-time access to your HubSpot data.
• Ability to query your data using natural language.
• Improved data security with read-only access.
• Simplified data modeling with SQL-based access.

Q: What kind of questions can I ask Claude about my HubSpot data? A: You can ask a wide range of questions, such as:

• “What is the correlation between my closed won opportunities and the account industry?”
• “How many open tickets do I have in the SUPPORT project?”
• “Can you tell me what calendar events I have today?”

Q: Is the HubSpot MCP Server read-only or read/write? A: This specific MCP Server is read-only. However, CData offers a free (beta) read/write server with full capabilities, which you can find at https://www.cdata.com/solutions/mcp.

Q: What do I need to set up the HubSpot MCP Server? A: You will need:

• The HubSpot MCP Server files (from the GitHub repository).
• The CData JDBC Driver for HubSpot.
• A Claude Desktop client.
• A Java Runtime Environment (JRE).

Q: How do I configure the connection to my HubSpot data? A: You can use the Connection String utility provided by CData to configure the connection string. You will need to provide your HubSpot credentials and any other necessary information.

Q: What is a .prp file and why do I need it? A: A .prp file is a properties file that contains the configuration information for your JDBC connection, such as the driver path, driver class, JDBC URL, and table information. This file is used by the MCP Server to connect to your HubSpot data.

Q: How do I add the MCP Server to my Claude Desktop configuration? A: You need to edit the claude_desktop_config.json file and add an entry for the HubSpot MCP Server, specifying the command and arguments needed to run the server.

Q: I can’t see my CData MCP Server in Claude Desktop. What should I do? A: Make sure that you have fully quit Claude Desktop (using Task Manager on Windows or Activity Monitor on Mac) and restarted it. Also, verify that your configuration file is correctly placed and formatted.

Q: Claude Desktop is unable to retrieve data. What could be the problem? A: Ensure that you have configured your connection properly. Use the Connection String builder to create the connection string and copy it into the property (.prp) file. Also, verify that your HubSpot credentials are correct.

Q: Where can I get help if I’m having trouble connecting to my data source? A: You can contact the CData Support Team for assistance.

Q: Where can I get help if I’m having trouble using the MCP server? A: You can join the CData Community to ask questions and get support.

Q: What are the available tools exposed by the MCP Server? A: The available tools include:

• {servername}_get_tables: Retrieves a list of tables in the data source.
• {servername}_get_columns: Retrieves a list of columns for a specific table.
• {servername}_run_query: Executes a SQL SELECT query against the data source.

Q: What is the license for the MCP Server? A: This MCP server is licensed under the MIT License, meaning you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License.