model2data studio MCP
An MCP server for model2data studio that allows AI agents to list and describe data projects, preview up to 50 rows per table, and generate realistic synthetic data seeds from a schema. It enables agents to write full datasets and read rows back, supporting workflows where agents build dbt projects or dashboards before real data is available.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
What you can do with it
- List and describe existing data models
- Preview up to 50 rows per table
- Generate synthetic data seeds for dbt projects
- Read generated rows back into the agent context
Source and maintenance
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
model2data-studio 0.1.0
{
"version": "0.1.0",
"transport": "stdio",
"identifier": "model2data-studio",
"runtimeHint": "uvx",
"registryType": "pypi",
"registryBaseUrl": "https://pypi.org",
"packageArguments": [
{
"type": "positional",
"value": "mcp",
"description": "The subcommand that starts the MCP server over stdio."
}
],
"runtimeArguments": [
{
"name": "--from",
"type": "named",
"value": "model2data-studio[mcp]",
"description": "The MCP SDK is an optional extra of the package."
}
],
"environmentVariables": [
{
"name": "MODEL2DATA_STUDIO_KEY",
"format": "string",
"isRequired": true,
"description": "A studio API key, created in the studio's account menu (Pro plan)."
},
{
"name": "MODEL2DATA_STUDIO_URL",
"format": "string",
"default": "https://studio.jbanalytica.com",
"description": "The studio to talk to. Only for a self-hosted studio."
}
]
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Connect from your client
Each snippet configures the same source-provided package; replace placeholders before use.
Cursor
{
"mcpServers": {
"model2data-studio-mcp": {
"command": "uvx",
"args": [
"model2data-studio==0.1.0",
"mcp"
],
"env": {
"MODEL2DATA_STUDIO_KEY": "<YOUR_MODEL2DATA_STUDIO_KEY>",
"MODEL2DATA_STUDIO_URL": "<YOUR_MODEL2DATA_STUDIO_URL>"
}
}
}
}Cline
{
"mcpServers": {
"model2data-studio-mcp": {
"command": "uvx",
"args": [
"model2data-studio==0.1.0",
"mcp"
],
"env": {
"MODEL2DATA_STUDIO_KEY": "<YOUR_MODEL2DATA_STUDIO_KEY>",
"MODEL2DATA_STUDIO_URL": "<YOUR_MODEL2DATA_STUDIO_URL>"
}
}
}
}VS Code
{
"servers": {
"model2data-studio-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"model2data-studio==0.1.0",
"mcp"
],
"env": {
"MODEL2DATA_STUDIO_KEY": "<YOUR_MODEL2DATA_STUDIO_KEY>",
"MODEL2DATA_STUDIO_URL": "<YOUR_MODEL2DATA_STUDIO_URL>"
}
}
}
}Claude Desktop
{
"mcpServers": {
"model2data-studio-mcp": {
"command": "uvx",
"args": [
"model2data-studio==0.1.0",
"mcp"
],
"env": {
"MODEL2DATA_STUDIO_KEY": "<YOUR_MODEL2DATA_STUDIO_KEY>",
"MODEL2DATA_STUDIO_URL": "<YOUR_MODEL2DATA_STUDIO_URL>"
}
}
}
}Let your agent find its tools
Find servers like model2data studio MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.