BonnardSAFE
Archived. Earlier Bonnard product. Current: bonnard.dev / @bonnard/mcp-charts
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[!IMPORTANT] This repository is archived and no longer maintained. It was part of an earlier version of Bonnard. Our current products live at [bonnard.dev](https://bonnard.dev). Start with [`@bonnard/mcp-charts`](https://github.com/bonnard-data/mcp-charts). Questions: [email protected]
Self-hosted semantic layer for AI agents.
Docs · CLI · Discord · Website
Bonnard is an agent-native semantic layer — one set of metric definitions, every consumer (AI agents, apps, dashboards) gets the same governed answer. This repo is the self-hosted Docker deployment: run Bonnard on your own infrastructure with no cloud account needed.
Quick Start
# 1. Scaffold project npx @bonnard/cli init --self-hosted # 2
b305e4d75adcOBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add oss --env ADMIN_TOKEN=${ADMIN_TOKEN} --env CUBE_API_SECRET=${CUBE_API_SECRET} -- npx -y @bonnard/[email protected]{
"mcpServers": {
"oss": {
"command": "npx",
"args": [
"-y",
"@bonnard/[email protected]"
],
"env": {
"ADMIN_TOKEN": "${ADMIN_TOKEN}",
"CUBE_API_SECRET": "${CUBE_API_SECRET}"
}
}
}
}Exposed tools (6)
6 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
describe_field | read | Get detailed metadata for a specific field including its type, format, and description. Use this to understand what a measure or dimension means before querying it. The field name must be fully qualified: |
explore_schema | read | Discover available data sources (views), their measures, dimensions, and segments. **Always call this before querying.** Field names returned here are the exact names to use in the query tool. Usage: - No parameters → list all sources with summary counts. Start here. - \ |
orders | read | All customer orders |
orders.completed | read | Only completed orders |
query | read | Primary tool for fetching data from the semantic layer. Use explore_schema first to discover field names. All field names must be fully qualified: |
sql_query | read |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (4 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (3)
cwd: new URL("../../..", import.meta.url).pathname,import type { CubeMetaItem } from "../../cube/client.js";express, cors, @modelcontextprotocol/sdk, jose, zod, tsx, typescript, @types/node
Gates applied: no_behavioural_pass.
b305e4d75adcfull audit observations/trust-audit/mcp-server/bonnard-data__bonnard-3.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | b305e4d75adc | SAFE | B | 89 | first audit |
Questions
What is the Bonnard MCP server?
Archived. Earlier Bonnard product. Current: bonnard.dev / @bonnard/mcp-charts
What tools does Bonnard expose?
6 in total: 6 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Bonnard safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Bonnard need?
It reads ADMIN_TOKEN and CUBE_API_SECRET from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Bonnard run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on npm as @bonnard/oss at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (b305e4d75adc), read on 2026-10-08. The repository is watched and re-audited when it changes.