What are the prerequisites?
Python >= 3.10.0, uvx installed, and an MCP client (e.g., VS Code, Cursor, Claude Desktop).
@singlestore-labs
Basic information
MCP server for interacting with SingleStore Management API and services
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-server-singlestore": {
"command": "uvx",
"args": [
"singlestore-mcp-server",
"init",
"--client=claude-desktop"
]
}
}
}Retrieve details about the current user
Retrieve details about the user's current organization
Choose from available organizations (only available when API key environment variable is not set)
Set the active organization (only available when API key environment variable is not set)
Retrieve details about the workspace groups accessible to the user
Retrieve details about the workspaces in a specific workspace group
Resume a suspended workspace
List all starter workspaces accessible to the user
Create a new starter workspace
Terminate an existing starter workspace
Retrieve a list of all regions that support workspaces
Retrieve a list of shared tier regions
Execute SQL operations on a connected workspace
Create a new notebook file in SingleStore Spaces
Upload a notebook file to SingleStore Spaces
Create a scheduled job from a notebook
Retrieve details of an existing job
Delete an existing job
List files and folders in a Stage deployment's file system
Get a file from Stage by path
Create a folder in Stage
Upload a file to Stage with text content
Move or rename a file or folder in Stage
Delete a file or folder from Stage
The SingleStore MCP Server implements the Model Context Protocol (MCP) to enable seamless integration between large language models and SingleStore. It allows users to interact with SingleStore using natural language through any compatible MCP client, making complex operations easier.
Install with uvx singlestore-mcp-server start or use automatic setup commands like uvx singlestore-mcp-server init --client=claude-desktop. No API keys or environment variables are needed – authentication is handled via browser OAuth. For Docker, an API key is required. The server works with Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Gemini CLI, LM Studio, Goose, and Qodo Gen.
Python >= 3.10.0, uvx installed, and an MCP client (e.g., VS Code, Cursor, Claude Desktop).
No. The server automatically handles authentication via browser OAuth when started. An API key is required only when running the server in Docker.
Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Gemini CLI, LM Studio, Goose, and Qodo Gen are explicitly supported.
Yes, but OAuth is not supported in Docker containers, so you must provide an API key via the `MCP_API_KEY` environment variable.
The `choose_organization` and `set_organization` tools are only available when the API key environment variable is not set, allowing interactive organization selection during OAuth.

Model Context Protocol Servers
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi
Comments