bonnard-data/bonnard-cli
Open-source agentic schema CLI. Optimised for claude code, gemini, codex and co-pilot. Skills included.
Platform-specific configuration:
{
"mcpServers": {
"bonnard-cli": {
"command": "npx",
"args": [
"-y",
"bonnard-cli"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
<p align="center"> <a href="https://www.bonnard.dev"> <picture> <source media="(prefers-color-scheme: dark)" srcset="./assets/banner-dark.png" /> <source media="(prefers-color-scheme: light)" srcset="./assets/banner-light.png" /> </picture> </a> </p>
<p align="center"> <strong>Agent-native analytics. One schema, many surfaces.</strong> </p>
<p align="center"> <a href="https://www.npmjs.com/package/@bonnard/cli"></a> <a href="https://github.com/bonnard-data/bonnard-cli/blob/main/LICENSE"></a> <a href="https://discord.com/invite/RQuvjGRz"></a> </p>
<p align="center"> <a href="https://docs.bonnard.dev/docs/">Docs</a> · <a href="https://docs.bonnard.dev/docs/getting-started">Getting Started</a> · <a href="https://docs.bonnard.dev/docs/changelog">Changelog</a> · <a href="https://discord.com/invite/RQuvjGRz">Discord</a> · <a href="https://www.bonnard.dev">Website</a> </p>
---
BI tools serve one UI. Bonnard serves everything. Agents over MCP, apps over SDK, dashboards in markdown, internal tools via REST. One set of metric definitions, every consumer gets the same governed answer.
<p align="center"> </p>
Traditional semantic layers were built for dashboards and retrofitted for AI. Agents get different answers than dashboards, metrics drift across tools, and
Loading reviews...