Spotdb MCP server
{
"mcpServers": {
"aliengiraffe-spotdb": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"docker.io/aliengiraffe/spotdb:0.1.0"
]
}
}
}{
"mcpServers": {
"aliengiraffe-spotdb": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"docker.io/aliengiraffe/spotdb:0.1.0"
]
}
}
}{
"mcpServers": {
"aliengiraffe-spotdb": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"docker.io/aliengiraffe/spotdb:0.1.0"
]
}
}
}{
"servers": {
"aliengiraffe-spotdb": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"docker.io/aliengiraffe/spotdb:0.1.0"
]
}
}
}{
"mcpServers": {
"aliengiraffe-spotdb": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"docker.io/aliengiraffe/spotdb:0.1.0"
]
}
}
}file .mcp.json (in your project root)file claude_desktop_config.jsonfile ~/.cursor/mcp.jsonfile .vscode/mcp.jsonfile ~/.codeium/windsurf/mcp_config.jsonversion 0.1.0
What it does
SpotDB is an ephemeral data sandbox that provides isolated, temporary database environments for AI workflows and data exploration. It exposes data through both MCP and REST APIs, with built-in guardrails and security to prevent accidental modification and enforce privacy constraints.
- Upload CSV data into temporary isolated databases and query them safely without touching production systems.
- Give AI agents and LLMs controlled access to data for analysis while enforcing guardrails that prevent unauthorized modifications.
- Create point-in-time snapshots of data states and recover or continue workflows from previous checkpoints.
Tools this server exposes
| Tool | Does |
|---|---|
| upload | Upload a CSV file to create a new table in the sandbox. |
| query | Execute SQL queries against tables in the sandbox. |
| snapshot | Capture and store data snapshots or recover to a previous state. |
Before you enable it
An MCP server runs with whatever access you give it. Start with a development account rather than production, and check which tools the server exposes before you let an agent call them unattended.