- Home
- MCP servers
- SingleStore
SingleStore
- other
0
GitHub Stars
other
Language
7 months ago
First Indexed
3 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"cdatasoftware-singlestore-mcp-server-by-cdata": {
"command": "java",
"args": [
"-jar",
"/PATH/TO/CDataMCP-jar-with-dependencies.jar",
"/PATH/TO/Salesforce.prp"
]
}
}
}You can query live SingleStore data through a dedicated MCP server that wraps the CData JDBC Driver. This read-only MCP server lets large language models fetch up-to-date data using natural language queries without writing SQL, making it easy to surface insights from your SingleStore databases.
How to use
You interact with the MCP server through an MCP client. Once the server is running and connected to your SingleStore data source, you can ask questions in natural language and request data operations. Typical workflows include asking for summary analyses, counts, lists of records, or joins across tables identified by the server. The built-in tools handle common data discovery tasks (like listing tables and columns) and execute read-only queries to retrieve results. You do not need to craft SQL; simply describe what you want and the client will translate it into the appropriate read operations.
What you can do with the MCP server
- Discover available tables and their columns
- Ask questions that relate to live data in SingleStore (e.g., opportunities, tickets, calendar events)
- Retrieve dataset slices via read-only queries without writing SQL
- Ask for counts, aggregates, and basic analytics across tables
Available interactions with the MCP server
The server exposes read-only tools that allow you to discover data structures and retrieve data. You can ask the client to list tables, list columns for a table, and run read-only queries. For example, you might query for the number of open items in a project, or summarize opportunities by industry, without ever issuing SQL syntax.
Available tools
singlestore_get_tables
Retrieves a list of tables available in the data source. The output is in CSV format, with the first line containing column headers.
singlestore_get_columns
Retrieves a list of columns for a specified table. The output is in CSV format, with the first line containing column headers.
singlestore_run_query
Executes a SQL SELECT query against the data source and returns the results.