Backend integration layer that connects your Metabase instance with AI assistants using the Model Context Protocol (MCP)
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add metabase-server-cw-codewalnut -- uv venv .venv~/.codex/config.toml
[mcp_servers.metabase-server-cw-codewalnut]
command = "uv"
args = ["venv", ".venv"]
# codex mcp add metabase-server-cw-codewalnut -- uv venv .venv~/.cursor/mcp.json
{
"mcpServers": {
"metabase-server-cw-codewalnut": {
"command": "uv",
"args": [
"venv",
".venv"
]
}
}
}.vscode/mcp.json
{
"servers": {
"metabase-server-cw-codewalnut": {
"type": "stdio",
"command": "uv",
"args": [
"venv",
".venv"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"metabase-server-cw-codewalnut": {
"command": "uv",
"args": [
"venv",
".venv"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"metabase-server-cw-codewalnut": {
"command": "uv",
"args": [
"venv",
".venv"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"metabase-server-cw-codewalnut": {
"command": "uv",
"args": [
"venv",
".venv"
]
}
}
}