Manual setup required. The maintainer's config contains paths only you know - edit the placeholders below before adding it to Claude Code.
1
Prepare the server locally
Run this once before adding it to Claude Code.
git clone https://github.com/bonnard-data/bonnard
cd bonnardThen follow the repository README for any remaining dependency or build steps.
2
Register it in Claude Code
claude mcp add --transport http -H "Authorization: Bearer your-secret-token-here" bonnard https://bonnard.example.com/mcpReplace any placeholder paths in the command with the real path on your machine.
Environment 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 -dConare · memory for coding agents
Keep 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.
Remember this setup$npx conare@latest