bonnard-cli
CLI for deploying and querying a governed semantic/metrics layer for agentic analytics. Provides commands to scaffold projects, connect data sources, validate models, deploy with versioning/history, run queries, and set up an MCP server for governed agent queries, along with markdown dashboard tooling and programmatic access via a companion SDK/React packages.
Score Breakdown
⚙ Agent Friendliness
🔒 Security
Authentication exists conceptually (login + API keys) but scope/granularity and enforcement details are not described in the provided content. Transport security (HTTPS/TLS) is not explicitly stated. CLI likely relies on environment variables/config for secrets, but there is no explicit evidence about logging/redaction. Dependency list is small but no vulnerability/CVE status is provided.
⚡ Reliability
Best When
You want a single governed metric schema shared across LLM agents (via MCP), applications (via SDK/REST), and dashboards (markdown) to avoid metric drift and inconsistent definitions.
Avoid When
You only need ad-hoc SQL/BI access and do not want the overhead of modeling, deployment/versioning, and authentication/setup.
Use Cases
- • Define and govern metrics/dimensions once and reuse across agents, BI dashboards, and applications
- • Enable text-to-SQL / JSON/SQL querying against a semantic layer from the terminal and via APIs
- • Serve governed metric context to LLM agents via an MCP server
- • Build and deploy markdown-based dashboards with shared metric definitions
- • Automate semantic-layer deployment in CI/CD with diff/annotations/version history
Not For
- • A simple one-off BI tool with no need for a shared semantic/metrics layer
- • Use as a standalone data warehouse client without an existing data modeling workflow
- • Environments that require strict, verified compliance guarantees without reviewing the underlying service
Interface
Authentication
README indicates a login flow and the ability to create publishable/secret API keys, but does not describe OAuth/scopes or fine-grained permission model in the provided content.
Pricing
No pricing details present in the provided README content.
Agent Metadata
Known Gotchas
- ⚠ LLM agents may produce metric queries that rely on correct semantic-model definitions; ensure models are validated/deployed before agent usage.
- ⚠ If the semantic layer is updated, agents may need to pull the latest deployed models/configs to avoid stale context.
- ⚠ Agents should use the MCP/server or provided query endpoints rather than bypassing governance with raw warehouse access.
Alternatives
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for bonnard-cli.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
Package Brief
Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.
Delivered within 10 minutes
Score Monitoring
Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.
Continuous monitoring
Scores are editorial opinions as of 2026-03-30.