Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/jerichosequitin/metabase-mcp/agents-mdgit clone --depth 1 https://github.com/jerichosequitin/metabase-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/jerichosequitin/metabase-mcp/agents-md)<a href="https://agentmods.dev/instructions/jerichosequitin/metabase-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jerichosequitin/metabase-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00599 | $0.00599 |
| Opus 5 | $0.00300 | $0.00300 |
| Sonnet 5 | $0.00120 | $0.00120 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
metabase-mcp AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for agents when working on this repository.
Project Overview
TypeScript MCP server providing AI assistants with optimized access to Metabase analytics data.
Key Files
src/index.ts- Entry pointsrc/server.ts- MCP server with tool/resource handlerssrc/api.ts- Metabase API client with cachingsrc/handlers/- Tool handlers (search, list, retrieve, execute, export, clearCache)src/types/- TypeScript definitionssrc/config.ts- Environment validation
Commands
# Build
npm run build # Full build with validation + tests
npm run build:fast # TypeScript only (dev)
# Quality
npm run validate # type-check + lint + format check
npm run lint:fix # Auto-fix lint issues
# Test
npm test # Run tests
npm run test:coverage # With 80% threshold
# Run
npm start # Start server
npm run inspector # Debug with MCP Inspector
Configuration
# Required (choose one auth method)
METABASE_URL=https://your-instance.com
METABASE_API_KEY=your_key # Recommended
# OR
[email protected]
METABASE_PASSWORD=password
# Optional
LOG_LEVEL=info # debug, info, warn, error, fatal (debug enables pretty JSON)
CACHE_TTL_MS=600000 # 10 min default
REQUEST_TIMEOUT_MS=600000 # 10 min default
EXPORT_DIRECTORY=~/Downloads/Metabase
METABASE_READ_ONLY_MODE=true # Restrict to SELECT queries
Rules
Code Style
- Strict TypeScript (
noImplicitAny,noUnusedLocals,noUnusedParameters) - ESLint + Prettier enforced
- No emojis in code, docs, or tool descriptions
Testing
- Tests in
tests/mirrorsrc/handlers/structure - Mock API at handler level, not API client level
- Do NOT create
tests/api.test.ts- API methods tested through handlers - 80% coverage threshold enforced
MCP Design Pattern
Never implement the same functionality as both Resource and Tool.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 87 lines · 599 tokens per session scan A 6dd28dc52849
metabase-mcp AGENTS.md is an instructions file published in the GitHub repository jerichosequitin/metabase-mcp (87 stars, last pushed 23d ago), licensed MIT. It adds 599 tokens to every session, about $0.0030 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.