Bernstein is an open-source governance layer for AI agents that applies written policies, schedules agent work deterministically, controls approvals, and records verifiable execution history. It is used to coordinate CLI coding agents and other agent workloads, including parallel runs and offline review, while the catalogue entries provide its agent workflows and controls.
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.
git clone --depth 1 https://github.com/sipyourdrink-ltd/bernsteinInstalling this writes the configuration, not the program: `bernstein` has to be on your PATH already, or the server will not start.
Wrote 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/mcp/sipyourdrink-ltd/bernstein/bernstein)<a href="https://agentmods.dev/mcp/sipyourdrink-ltd/bernstein/bernstein"><img src="https://agentmods.dev/badge/mcp/sipyourdrink-ltd/bernstein/bernstein/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/sipyourdrink-ltd/bernstein/bernstein"><img src="https://agentmods.dev/badge/mcp/sipyourdrink-ltd/bernstein/bernstein.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
bernstein 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 1mo 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.
What it actually says
{
"bernstein": {
"command": "bernstein",
"args": [
"mcp"
]
}
}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.
- 1mo ago First seen · 8 lines scan A 0072df851ebe
bernstein is an MCP server published in the GitHub repository sipyourdrink-ltd/bernstein (1,332 stars, last pushed today), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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 mcp servers, from other repositories
ledger
Perseus Ledger: verifiable, hash-chained provenance for autonomous-system events and resource allocation. Runs locally from the perseus-ledger Python package.
mcp-evidence-ledger
MCP server "mcp-evidence-ledger" as configured in brianpelow/mcp-evidence-ledger. Runs locally from the mcp-evidence-ledger Python package.
aegis
Auto-instrument AI agent frameworks with runtime security. One line to govern LangChain, CrewAI, OpenAI, Anthropic — injection blocking, PII masking, action policy, audit trail. Zero code changes. Runs locally from the agent-aegis Python package. Needs 1 environment variable to run.
zotero
MCP server "zotero" as configured in scitex-ai/scitex-python. Launched with mcp-zotero. Needs 2 environment variables to run.
matrixscroll
MCP server for signed machine-action records, offline tool-surface checks, with device-agnostic custody and CNSA 2.0 Category 5 crypto (ML-DSA-87, ML-KEM-1024). Runs locally from the matrixscroll Python package.
sswp-mcp
MCP server "sswp-mcp" as configured in VrtxOmega/sswp-mcp. Runs locally from the sswp-mcp npm package.