SingleStore MCP Server

DatabasesPython

Interact with SingleStore databases and services using natural language

Available Tools

workspace_groups_info

Retrieve details about the workspace groups accessible to the user

workspaces_info

Retrieve details about the workspaces in a specific workspace group

workspaceGroupID

organization_info

Retrieve details about the user's current organization

list_of_regions

Retrieve a list of all regions that support workspaces for the user

execute_sql

Execute SQL operations on a connected workspace

workspace_group_identifierworkspace_identifierusernamepassworddatabasesql_query

list_virtual_workspaces

List all starter workspaces accessible to the user

create_virtual_workspace

Create a new starter workspace with a user

namedatabase_nameusernamepasswordworkspace_group

execute_sql_on_virtual_workspace

Execute SQL operations on a virtual workspace

virtual_workspace_idusernamepasswordsql_query

list_notebook_samples

List all notebook samples available in SingleStore Spaces

create_notebook

Create a new notebook in the user's personal space

notebook_namecontent

list_personal_files

List all files in the user's personal space

create_scheduled_job

Create a new scheduled job to run a notebook

namenotebook_pathschedule_modeexecution_interval_minutesstart_atdescriptioncreate_snapshotruntime_nameparameterstarget_config

get_job_details

Get details about a specific job

job_id

list_job_executions

List execution history for a specific job

job_idstartend

SingleStore MCP Server provides a seamless interface between large language models and SingleStore's database services. It enables users to manage workspaces, execute SQL queries, create notebooks, and schedule jobs through natural language interactions. With this integration, you can leverage the power of LLMs to interact with your SingleStore databases, making complex operations more accessible and efficient. The server supports a comprehensive set of tools for database management, SQL execution, and workspace administration.

Overview

SingleStore MCP Server enables natural language interaction with SingleStore databases and services through the Model Context Protocol (MCP). This integration allows you to use Claude Desktop, Cursor, or any compatible MCP client to perform database operations, manage workspaces, execute SQL queries, and more using conversational language.

Installation

There are three ways to install the SingleStore MCP Server:

Method 1: Using the Init Command (Recommended)

The simplest way to set up the server is with the initialization command:

uvx singlestore-mcp-server init

This command will:

Guide you through authentication
Automatically locate the configuration file for your platform
Create or update the configuration to include the SingleStore MCP server
Provide instructions for starting the server

You can also explicitly pass your SingleStore API key:

uvx singlestore-mcp-server init <SINGLESTORE_API_KEY>

To specify a client (e.g., claude or cursor), use the --client flag:

uvx singlestore-mcp-server init <SINGLESTORE_API_KEY> --client=<client>

Method 2: Installing via Smithery

To install automatically via Smithery:

npx -y @smithery/cli install @singlestore-labs/mcp-server-singlestore --client=<client>

Replace <client> with claude or cursor as needed.

Method 3: Manual Configuration

Add the following configuration to your client configuration file:

{
    "mcpServers": {
     "singlestore-mcp-server": {
      "command": "uvx",
      "args": [
        "singlestore-mcp-server",
        "start",
        "<SINGLESTORE_API_KEY>"
      ]
     }
    }
}

Replace <SINGLESTORE_API_KEY> with your actual SingleStore API key.

After making changes to the configuration, restart your client.

Requirements

Python >= v3.11.0
uvx installed in your Python environment
Claude Desktop, Cursor, or another supported LLM client
A SingleStore API key

Usage

Once installed, you can interact with SingleStore through natural language in your MCP-compatible client. For example:

"Show me all my workspace groups"
"Execute a SQL query to find the top 10 customers by revenue"
"Create a new starter workspace named 'analytics-test'"
"List all my notebook samples"

The server will interpret your requests and use the appropriate tools to fulfill them.

Docker Support

If you prefer to run the server in a Docker container:

Building the Docker Image

docker build -t mcp-server-singlestore .

Running the Docker Container

docker run -d \
  -p 8000:8000 \
  --name mcp-server \
  mcp-server-singlestore

This will start the server in a container, making it accessible on port 8000.