Log inSubmit server
Bernstein logo

Bernstein

by sipyourdrink-ltd

Deterministic MCP orchestration for parallel CLI coding agents with policy gates, isolated worktrees, and verifiable run records.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Bernstein

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "sipyourdrink-ltd-bernstein": {
      "command": "uvx",
      "args": [
        "bernstein"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

sipyourdrink-ltd/bernstein exposes a deterministic multi-agent orchestrator through MCP over stdio or HTTP/SSE. It schedules CLI coding agents in parallel, applies policy and approval gates, isolates coding tasks with Git worktrees, and records execution evidence for later verification. Reach for it when an MCP client needs governed, repeatable agent workflows rather than a single coding assistant session. Python 3.12+ is required, and the project is beta software under active development.

Use cases

  • Coordinate parallel coding agents from a YAML workflow
  • Enforce approval and role gates across agent tasks
  • Verify agent runs offline from recorded artifacts
  • Isolate concurrent coding work in Git worktrees
  • Generate audit evidence packs from multi-phase runs

Key features

  • Deterministic Python scheduler
  • stdio and HTTP/SSE MCP modes
  • Per-task Git worktree isolation
  • Policy, dependency, and merge gates
  • Replay journals and lineage records
  • Optional HMAC-chained audit receipts

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

25/26 checks healthy over the last 78d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 12d ago via OSV.dev · bernstein (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars1.3kStargazers on the source repository.
Last commitTodayMost recent push to the default branch.
Directory activity6 viewsConfig copies, upvotes, and views on AllMCPs.

How Bernstein works

What sipyourdrink-ltd/bernstein does

sipyourdrink-ltd/bernstein provides an MCP-facing governance layer for coordinating multiple AI agents. Its scheduler is implemented in Python rather than delegated to a language model, so the task graph and execution decisions can be reproduced from the workflow definition.

A workflow is described in YAML with phases, roles, dependencies, and execution conditions. The same framework can coordinate coding tasks and other deliverables, including research reports, datasets, action logs, operational results, and audit evidence packs. Agents can be selected from a broad set of CLI adapters, including Claude Code, Codex, Cursor, Gemini CLI, Aider, GitHub Copilot CLI, OpenHands, OpenCode, Goose, Qwen, and Ollama.

How it works

An MCP client connects to Bernstein through either stdio or HTTP/SSE. Bernstein then runs the declared workflow locally, starting eligible tasks according to the dependency graph and policy rules. Scheduling does not depend on an LLM choosing the next step.

Coding tasks receive separate Git worktrees by default, while artifact-oriented tasks use workspaces beneath .sdd/workspaces/. Tasks claim backlog state atomically, so agents do not share a mutable working directory unless worktree isolation is disabled. Merge gates and role restrictions can control what proceeds between phases.

Execution history is captured in a replay journal and a lineage record. The optional HMAC-chained audit log can add verifiable receipts when BERNSTEIN_AUDIT=1 is enabled. Hash mismatches identify the step where a replay diverges, allowing records to be checked offline from the generated artifacts.

Setup and configuration

Bernstein requires Python 3.12 or newer. The project publishes a Python package and a container image, and also provides an air-gap installation profile. Configure the MCP client to launch the server over stdio or connect to its HTTP/SSE endpoint, depending on the deployment layout.

Workflow definitions are YAML files. They specify the run name, phases, permitted roles, dependencies, and conditions for execution. Worktree isolation is enabled by default for coding tasks; stricter filesystem controls are available through optional sandbox backends. Set BERNSTEIN_AUDIT=1 when the opt-in HMAC audit trail is needed.

Tools and capabilities

  • Coordinate multiple CLI coding agents from one workflow.
  • Run independent tasks in parallel using a deterministic scheduler.
  • Apply role, phase, dependency, approval, and merge gates.
  • Isolate coding work with per-task Git worktrees.
  • Produce replayable journals, lineage records, and optional HMAC audit receipts.
  • Route work across more than 50 selectable CLI agent adapters and a generic prompt wrapper.
  • Handle non-code artifact contracts such as reports, datasets, and audit evidence packs.

Limitations and notes

The project is marked beta and is maintained by a solo maintainer. Minor releases may change interfaces, so deployments that depend on Bernstein should pin a version. The scheduler and audit records are local and file-based; the project does not use a SaaS data plane.

Hardware-key evidence features include offline PIV custody and FIDO2 approval verifiers, with pinned trust and explicit time. Token custody does not increase TRACE trust levels. Worktree isolation can be disabled, but doing so makes tasks run in the shared checkout rather than separate worktrees.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Bernstein

sipyourdrink-ltd/bernstein is an MCP server that connects MCP clients to Bernstein's deterministic multi-agent orchestrator. Its main capabilities coordinate CLI coding agents such as Claude Code, Codex, Cursor, and Gemini CLI, while providing parallel scheduling, policy gates, worktree isolation, and recorded run evidence.

Install it in a Python 3.12-or-newer environment using the project's Python package or container image, then configure an MCP client to use its stdio or HTTP/SSE interface. An air-gap installation profile is also available.

Yes, Bernstein lists Cursor among its supported CLI agent adapters and exposes its orchestrator to MCP clients. Connect Cursor to the Bernstein MCP server using the supported stdio or HTTP/SSE transport.

Set `BERNSTEIN_AUDIT=1` before starting the server. Bernstein then enables its opt-in HMAC-chained audit log, whose receipts can be verified offline.

Yes, coding tasks use separate Git worktrees by default. Tasks do not share a mutable workspace unless worktree isolation is disabled; stricter filesystem enforcement can be added through optional sandbox backends.

Related MCP servers

All in Coding Agents All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewBernstein AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/sipyourdrink-ltd-bernstein?style=directory)](https://allmcps.com/mcp/sipyourdrink-ltd-bernstein)
HTML Embed
<a href="https://allmcps.com/mcp/sipyourdrink-ltd-bernstein"><img src="https://allmcps.com/api/badge/sipyourdrink-ltd-bernstein?style=directory" alt="Bernstein on AllMCPs" /></a>