singlestore_labs_mcp_server_singlestore

singlestore_labs_mcp_server_singlestore

by singlestore-labs
An MCP server for seamless interaction with SingleStore Management API and services using natural language.

SingleStore MCP Server Integration

License: MIT
smithery badge

The SingleStore MCP Server is a powerful tool designed to facilitate seamless interaction with the SingleStore Management API and services using the Model Context Protocol (MCP). This implementation allows users to perform complex database operations through natural language commands, making it easier to manage and query data in SingleStore.

Overview

The MCP Server enables integration with SingleStore, allowing users to interact with the database using natural language commands via compatible MCP clients like Claude Desktop. This implementation provides a standardized protocol for managing context between large language models (LLMs) and external systems, streamlining database operations.

Quickstart

Installing via Smithery

To install the MCP Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @singlestore-labs/mcp-server-singlestore --client claude

Clone the Repository

To set up the server locally:

git clone https://github.com/singlestore-labs/mcp-server-singlestore.git
cd mcp-server-singlestore
pip install -e .

Install via pip

Alternatively, install the package using pip:

pip install singlestore-mcp-server

Run the server using the command singlestore-mcp-client.

Components

Tools

The MCP Server implements the following tools:

  • workspace_groups_info: Retrieve details about accessible workspace groups.
  • workspaces_info: Retrieve details about workspaces in a specific workspace group.
  • organization_info: Retrieve details about the user's organization.
  • list_of_regions: Retrieve a list of all supported regions.
  • execute_sql: Execute SQL operations on a connected workspace.
  • list_virtual_workspaces: List all starter workspaces.
  • create_virtual_workspace: Create a new starter workspace.
  • execute_sql_on_virtual_workspace: Execute SQL operations on a virtual workspace.
  • list_notebook_samples: List all notebook samples available in SingleStore Spaces.
  • create_notebook: Create a new notebook in the user's personal space.
  • list_personal_files: List all files in the user's personal space.
  • create_scheduled_job: Create a new scheduled job to run a notebook.
  • get_job_details: Get details about a specific job.
  • list_job_executions: List execution history for a specific job.

Configuration

The server requires the following environment variables:

# SingleStore's management API key (required)
SINGLESTORE_API_KEY=your_api_key_here

# Database credentials (optional - can be provided as input parameters)
SINGLESTORE_DB_USERNAME=your_db_username_here
SINGLESTORE_DB_PASSWORD=your_db_password_here

About

The SingleStore MCP Server is designed to simplify interactions with the SingleStore Management API and services using the Model Context Protocol. It provides a seamless way to manage and query data using natural language commands.

Resources

Contributors

Languages

  • Python: 98.2%
  • Dockerfile: 1.2%
  • Jupyter Notebook: 0.6%

Features & Capabilities

Categories
mcp_server model_context_protocol python docker api_integration singlestore claude search sql

Implementation Details

Stats

0 Views
2 GitHub Stars

Repository Info

singlestore-labs Organization

Similar MCP Servers

continuedev_continue by continuedev
25049
21423
9300