ToolTrust
C27/100
sipyourdrink-ltd

bernstein

mcp3.13.0

@sipyourdrink-ltd

Deterministic orchestrator for CLI coding agents (Claude Code, Codex, Gemini CLI, +40 more). No model in the coordination loop, so parallel runs in per-task git worktrees replay byte-identically. Signed lineage plus an opt-in HMAC audit chain a reviewer checks offline, without rerunning it. Cluster mode, air-gap deploy. https://bernstein.run

By sipyourdrink-ltd | 26 findings | Scanned 10/15/2026 | tooltrust-scanner/v0.3.20 | 1.3k

Repository health

Popularity and maintenance signals alongside the security grade.

View repository
Stars

1.3k

current snapshot

Forks

185

current snapshot

Contributors

113

public GitHub contributors

Last commit

Oct 27, 2026

GitHub repository activity

Last release

Oct 24, 2026

v3.23.0

Release version

v3.23.0

Latest GitHub release

Stars trend

Daily star additions · githubarchive_bq · observed through Oct 25, 2026 · export updated Oct 29, 2026

25d
2026-08-202026-10-23

Pull request activity

Weekly PR events · githubarchive_bq · observed through Oct 25, 2026 · export updated Oct 29, 2026

2026-06-292026-10-19

Data quality: observed_events. Charts show observed events, not a reconstructed historical total.

PythonApache-2.0Developer ToolsLast scan Oct 15, 2026
1 Critical4 Low21 Info

Risk Summary

Needs Approval

Dep Visibility plus Excessive Permissions raises enough risk that this tool should not be auto-trusted.

Potential impact: This finding indicates the tool should be reviewed before it is trusted.

Recommended action: Keep this tool behind manual approval and avoid unattended runs until the risky capabilities are narrowed or removed.

Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.

Security Findings (26)

  • CriticalAS-006

    💻Arbitrary Code Execution

    heuristic signal

    load_skill:tool name or description implies arbitrary script/code execution (evaluate_script, execute javascript, etc.)

    Fix: This tool can execute arbitrary code or shell commands on the host system. Remove it unless strictly required. If kept: (1) restrict access to trusted users/agents only, (2) require human approval before each invocation (Claude Desktop: set approval_required: true; other clients: enable equivalent confirmation), (3) use the most restrictive sandbox or read-only mode available, and (4) never expose this tool to untrusted input sources.

  • LowAS-011

    ℹ️Missing Rate-Limit / Timeout ×4

    tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration

    bernstein_create_subtaskbernstein_post_artifactbernstein_updateload_skill

    Fix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.

  • InfoAS-014

    ℹ️Dependency Inventory Unavailable ×14

    Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.

    bernstein_approvebernstein_claimbernstein_contextbernstein_costbernstein_create_subtaskbernstein_healthbernstein_post_artifactbernstein_runbernstein_statusbernstein_stopbernstein_task_handlebernstein_tasksbernstein_updateload_skill

    Fix: Review and remediate the identified issue.

  • InfoAS-002

    ⚠️Excessive Permissions ×7

    declared capabilities: filesystem access

    bernstein_contextbernstein_stopbernstein_task_handle

    declared capabilities: code/command execution, filesystem access

    bernstein_create_subtask

    declared capabilities: network access, HTTP requests

    bernstein_post_artifact

    declared capabilities: filesystem access, HTTP requests

    bernstein_update

    declared capabilities: code/command execution, network access, filesystem access

    load_skill

    Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.

Scan this tool yourself

Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.

Install once, then scan any MCP server:

$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash
$ tooltrust-scanner scan --server "npx -y bernstein"

Adjust the package name if your npm registry name differs from the tool ID. View source

Add badge to your README

Copy this Markdown to show your ToolTrust grade on GitHub.

[![ToolTrust Grade C](https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-directory/main/docs/badges/grade-c.svg)](https://github.com/AgentSafe-AI/tooltrust-directory)