google/chrome-enterprise-premium-mcp is a Model Context Protocol server that lets compatible AI agents inspect and configure Chrome Enterprise Premium security settings, including data-loss prevention, threat protection, access controls, telemetry, and licensing. It is intended for administrators managing Chrome Enterprise environments, and the catalogue entries operate the server through MCP.
Borrowing it
Nothing to install: this file belongs to google/chrome-enterprise-premium-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/google/chrome-enterprise-premium-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/google/chrome-enterprise-premium-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/google/chrome-enterprise-premium-mcp/agents-md)<a href="https://agentmods.dev/instructions/google/chrome-enterprise-premium-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/google/chrome-enterprise-premium-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 | $0.01018 | $0.01018 |
| Opus 5 | $0.00509 | $0.00509 |
| Sonnet 5 | $0.00204 | $0.00204 |
| Haiku 4.5 | $0.00102 | $0.00102 |
Grade A, and why
chrome-enterprise-premium-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 7d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Read this. The conventions below catch what an agent will probably get wrong
without being told. For everything else, see README.md, CONTRIBUTING.md,
docs/architecture.md, and the per-directory READMEs (lib/, tools/,
test/).
AGENTS.md is the canonical steering file. CLAUDE.md and GEMINI.md at
the repo root are symlinks to it, so Claude Code, Gemini CLI, Codex, Cursor,
and Aider all read the same content.
Why a separate
gemini-extension/CONTEXT.md? That file is the runtime persona for the Gemini Extension; its content is the end-user persona, not contributor steering. The filename is deliberately notGEMINI.md. Otherwise Gemini CLI's workspace scanner would pull the persona into a contributor's coding session.
Code style
Lint setup is strict. To pass on the first try:
- No semicolons. Single quotes. 120-char lines. Trailing commas
everywhere.
arrowParens: 'avoid'. Full config in.prettierrc. - Apache 2.0 copyright header on every
.jsfile.eslint-plugin-noticerewrites a missing or wrong header on lint; copy the banner from any neighbor file when creating a new one. ESLint sets the year fromnew Date().getFullYear()ineslint.config.mjs, so use the current year. - JSDoc is required on top-level
functionandclassdeclarations, methods, and exported functions. Each block has a description, every@paramtyped and described, and@returnstyped and described. Arrow functions, function expressions, and test files (test/**,**/*.test.js) are exempt. - ESM only.
import/export. Norequire(). ===always;==is a lint error.nocommitand@nocommitmarkers fail lint.
Tests
- Use Node's built-in
node:testandnode:assert. Do not add jest, mocha, vitest, sinon, nock, or msw. - For new tests, use
test/local/, nottest/unit/. Theunit/directory is reserved for the feature-flag and connector-enablement unit tests; everything else, including API-client and tool tests, is inlocal/. Seetest/README.md. - Add HTTP fakes by editing
test/helpers/fake-api-server.js. Register routes there; let the real client classes target them through theirrootUrloverride. Don't mock at theaxiosorgoogleapislayer. CEP_BACKEND=fakeis the default for everynpm runscript excepttest:integration:real. The real-backend suite has two prerequisites: ADC plus a real Workspace tenant. Only run it intentionally.- Delete tools (
delete_agent_dlp_rule,delete_detector) are gated byEXPERIMENT_DELETE_TOOL_ENABLED=true. Set it in any delete-tool test.
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.
- 7d ago First seen · 78 lines · 1,018 tokens per session scan A 4f1f6f59e783
chrome-enterprise-premium-mcp AGENTS.md is an instructions file published in the GitHub repository google/chrome-enterprise-premium-mcp (10 stars, last pushed 12d ago), licensed Apache-2.0. It adds 1,018 tokens to every session, about $0.0051 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 2026-08-31.
Other instructions, from other repositories
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 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).
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.
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.