Coding agents · MCP server
Bernstein: MCP server, setup and security
Bernstein is an open-source MCP server that lets an AI agent orchestrate CLI coding agents with git worktrees and cost-aware routing. Its repository has 1,330 stars and its last commit is from October 24, 2026 and it is licensed under Apache-2.0.
What Bernstein does
According to its repository: “Deterministic orchestrator for CLI coding agents such as Claude Code, Codex and Aider, with per-agent git worktrees, an audit trail and cost-aware routing.”
An MCP server gives an AI agent extra tools it calls during the conversation: the agent reads their description, decides to use them and gets the result back. Bernstein is listed under Coding agents, a category of 151 servers in the directory, where it ranks #12 by stars.
Topics declared by the repository: agent-orchestrator, deterministic-replay, air-gap, audit-trail, provenance, reproducibility.
Installing and connecting Bernstein
Distribution modes declared in the official MCP registry:
- PyPI package (Python, started with
uvxorpip) - Docker (OCI) image
Like any MCP server, you declare it in your client's configuration (Claude Desktop, Claude Code, Cursor, VS Code, Codex…): a name, the command that starts it or its URL, and any environment variables. The client then starts it and lists its tools. Project language: Python. Listed systems: macOS, Windows, Linux.
Security: what to check
An MCP server runs code with the rights you give it, and the model reads its tool descriptions: a malicious or compromised server can hijack the agent. Read the code, or pick a maintained and widely used server, before connecting it.
None of the risk signals we track (system access, secrets, missing licence, abandonment) applies to Bernstein. That does not replace reading the code.
Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.
Project activity and maintenance
Created on March 22, 2026, the sipyourdrink-ltd/bernstein repository has 1,330 stars and 185 forks, with 195 open issues. It has more stars than 93% of the servers in the directory. It received changes this month. Version published in the registry: 3.22.0 (October 15, 2026).
Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.
Verdict
Bernstein is one of the most solid servers in its category: followed, maintained and well framed.
Strengths
- Active project: recent commit
- Widely followed: 1.3K stars
- Listed in the official MCP registry
- Permissive licence (Apache-2.0)
Alternatives
- Desktop Commander10.1K ★
- Ouroboros6.3K ★
- Repomix29K ★
- Claude Code Ultimate Guide6.2K ★
- Harness1.4K ★
- Appllama3K ★
Learn more
Frequently asked questions
How do I install Bernstein?
Bernstein is distributed as PyPI package (Python, started with uvx or pip) and Docker (OCI) image. Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of sipyourdrink-ltd/bernstein.
Is Bernstein free?
The code is published under the Apache-2.0 licence and can be used free of charge.
Is Bernstein safe?
No risk signal found (system access, secrets, licence, abandonment). As with any MCP server, keep rights minimal and read the code before sensitive use.
Is it an official server?
Nothing says so: it is a project published by sipyourdrink-ltd on GitHub. Check who maintains it before giving it access.
What are the alternatives to Bernstein?
In the same category: Desktop Commander, Ouroboros, Repomix, and Claude Code Ultimate Guide.
Related articles
- Build your own MCP server in 30 minutesOctober 24, 2026
- Automate your inbox with an AI agentOctober 18, 2026
- MCP, A2A, and tool calling: agent protocols explainedOctober 17, 2026
- Build an AI agent with n8n, without codingOctober 16, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score