- Parquet MCP Server by CData
Parquet MCP Server by CData
What is Parquet MCP Server by CData?
Parquet MCP Server by CData is a read-only Model Context Protocol (MCP) server that allows large language models (LLMs) to query live data stored in Parquet format using natural language, without the need for SQL.
How to use Parquet MCP Server?
To use the Parquet MCP Server, clone the repository, build the server, install the CData JDBC Driver for Parquet, configure your connection, and run the server. You can then interact with the server through an AI client like Claude Desktop.
Key features of Parquet MCP Server?
- Read-only access to Parquet data via a simple MCP interface.
- Natural language querying capabilities for LLMs.
- Integration with CData JDBC Driver for seamless data access.
Use cases of Parquet MCP Server?
- Querying live data from Parquet files using natural language.
- Integrating with AI clients for data analysis and reporting.
- Simplifying data access for non-technical users.
FAQ from Parquet MCP Server?
- Can I write data using this server?
No, this server is read-only. For write capabilities, consider the full CData MCP Server for Parquet.
- Is there a trial version available?
Yes, you can access a free beta version of the CData MCP Server for Parquet.
- What types of data sources are supported?
The server supports various data sources, including Salesforce, and many others as listed in the documentation.
Server Config
{
"mcpServers": {
"{classname_dash}": {
"command": "PATH\\TO\\java.exe",
"args": [
"-jar",
"PATH\\TO\\CDataMCP-jar-with-dependencies.jar",
"PATH\\TO\\parquet.prp"
]
}
}
}