Updated March 2026
Install Bonnard
Pick your client, copy the command, done.
1
Add it to Claude Code
Run this in a terminal.
claude mcp add bonnard -- npx @bonnard/cli init --self-hostedEnvironment Variables
Set these before running Bonnard.
VariableDescriptionRequired
ADMIN_TOKENAuthentication token for API and MCP endpointsNoCUBEJS_DB_TYPEDatabase driver (postgres, duckdb, snowflake, bigquery, databricks, redshift, clickhouse)NoCUBEJS_DB_*Database connection settings (host, port, name, user, pass)NoTry It Out
After setup, try these prompts with your AI agent:
→Query the semantic layer to get the total revenue for the last quarter.
→List all available metrics and views defined in the Bonnard semantic layer.
→Compare the user growth metrics between this month and last month using the semantic layer.
→Fetch the top 10 products by sales volume from the connected data warehouse.
Prerequisites & system requirements
- An MCP-compatible client (Claude Code, Cursor, Windsurf, Claude Desktop, or Codex)
- Node.js 18+ with npm/npx installed
- Docker installed and running
Alternative installation methods
Docker
docker compose up -dKeep this setup from going cold
Save the docs, env vars, and workflow around Bonnard in Conare so Claude Code, Codex, and Cursor remember it next time.
Need the legacy visual installer? Open Conare IDE.