ModelsAtlas
Explore
Atlas / MCP servers / zenolab124 / Monet

MonetBLOCK

mcp/zenolab124/monet
MCP server by zenolab124 · agents · ai agent · anthropic · Audited 2026-10-07
⚑ Report / re-scanSource ↗

Monet — Multi-engine mission control for coding agents (Claude Code and Codex today). Browse, search, and drive your agent sessions from a native desktop app.

Verdict
BLOCK
Grade
D
Trust score
69 /100
Exposed tools
3 2r · 1w · 0d
Transport
—
License
MIT
Stars
283
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

Monet

Coding Agent 的多引擎指挥台——Claude Code 与 Codex 已同席

English

功能 • 安装 • 构建 • 隐私 • 常见问题

懒得读?把这行丢给你的 AI,它会替你判断、安装、排障: 读取 https://raw.githubusercontent.com/zenolab124/monet/main/llms.txt 如果你就是那个 AI:读取上面的 llms.txt,按其中指引为你的用户服务。

Monet 是什么?

你和 Coding Agent 的对话散落在不同终端、项目和会话记录里——想回看要翻,想并行要切,跑长任务还得反复回来确认进度。

Monet 把 Claude Code、Codex 等引擎收进一面墙:所有 Agent 会话可浏览、可搜索、可并行指挥。Agent 干活,Monet 给你眼睛和手。

为什么选 Monet?

引擎再多,一面墙。 Claude Code 与 Codex 共用一个档案馆、一套搜索和一面工作台,每个会话带引擎徽标随时分辨。赛马模式让同一道题跨引擎对拼,定时任务也能自由选择执行引擎——选引擎就像选模型一样自然。

像看盘一样指挥你的 Agent。 不限列数的并行会话横向铺开,监控轨上的状态、输出和 token 一眼可见;权限审批、回答提问、失

Read from source at commit f7106a4f5f53OBSERVED · 2026-10-07
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code
claude mcp add monet-tauri -- npx -y [email protected]
claude-desktop
{
  "mcpServers": {
    "monet-tauri": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ]
    }
  }
}
03

Exposed tools (3)

2 read · 1 write · 0 destructive.

ToolRiskDescription
Fastread1.5x speed
deploywriteDeploy project
reviewreadReview changes
04

Trust audit

BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

LayerWhat it checksResult
L0Provenance & inventoryWARN
L1Static analysis of the codeFAIL
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (13 observation(s))
Network
declared (5 observation(s))
Shell
declared (1 observation(s))
Dependencies
not all pinned
Secrets in source
none-found

Findings (14)

HIGHFilesystem / path · fs.credential_store · CWE-22, CWE-59
src/utils/dangerousOps.ts:49
'~/.ssh/',
Why it matters. touches a credential store
HIGHFilesystem / path · fs.credential_store · CWE-22, CWE-59
src/utils/dangerousOps.ts:50
'~/.aws/',
Why it matters. touches a credential store
HIGHFilesystem / path · fs.credential_store · CWE-22, CWE-59
src/utils/dangerousOps.ts:51
'~/.gnupg/',
Why it matters. touches a credential store
MEDIUMInventory / provenance · inv.binary · CWE-1104
src-tauri/icons/icon.icns
icon.icns
Why it matters. a compiled or binary member cannot be reviewed from source
Fix. ship source, or explain the binary in the README
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
scripts/bench/render-bench.mjs:24
import { renderMarkdownPlain, renderMarkdownCached } from '../../src/composables/useMarkdown.ts'
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src-tauri/src/background_services.rs:249
include_str!("../../src-widget/io.github.zenolab124.monet.widget-updater.plist");
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src-tauri/src/background_services.rs:250
const WIDGET_BUILD: &str = include_str!("../../src-widget/build.sh");
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src-tauri/src/background_services.rs:251
const TRAY_INFO: &str = include_str!("../../src-tray/Info.plist");
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src-tauri/src/background_services.rs:254
include_str!("../../src-widget/MonetWidgetExtension.entitlements");
LOWObfuscation / stealth · obf.decode_call · CWE-506, CWE-94
src/composables/useImageActions.ts:69
const binary = atob(result.data)
LOWObfuscation / stealth · obf.decode_call · CWE-506, CWE-94
src/composables/useWorkbenchCapture.ts:55
const bytes = Uint8Array.from(atob(payload), character => character.charCodeAt(0))
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@dnd-kit/helpers, @dnd-kit/vue, @mdit/plugin-katex, @shikijs/markdown-it, @tanstack/vue-virtual, @tauri-apps/api, @tauri-apps/plugin-dialog, @tauri-apps/plugin-notification
Why it matters. 31 dependency range(s) float
Fix. pin exact versions or ship a lockfile
LOWPrompt injection · review.instruction_override · CWE-94, CWE-1427
README.md
读取 https://raw.githubusercontent.com/zenolab124/monet/main/llms.txt
Why it matters. The README instructs any AI that reads it to fetch and follow instructions from an external URL (llms.txt), which is an instruction injection that could override the agent's own instructions or the user's intent.
Fix. rewrite it so the instruction says plainly what it does, and asks the user before it acts
LOWPrompt injection · review.instruction_override · CWE-94, CWE-1427
README.md
读取 https://raw.githubusercontent.com/zenolab124/monet/main/llms.txt 帮我排查 Monet 的问题
Why it matters. The FAQ repeats the same pattern, telling the AI agent to fetch external instructions from llms.txt to self-diagnose and file bug reports on the user's behalf.
Fix. rewrite it so the instruction says plainly what it does, and asks the user before it acts

Gates applied: no_behavioural_pass.

Audited 2026-10-07 · audit v0.4.1 · source sha f7106a4f5f53full audit observations/trust-audit/mcp-server/zenolab124__monet.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-07f7106a4f5f53BLOCKD69first audit
06

Questions

What is the Monet MCP server?

Monet — Multi-engine mission control for coding agents (Claude Code and Codex today). Browse, search, and drive your agent sessions from a native desktop app.

What tools does Monet expose?

3 in total: 2 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Monet safe to connect to an agent?

No — not without reading the findings first. The audit graded it D (69/100) and found 3 critical or high issues in the source. Each one is listed on this page with the file and line it is on.

What credentials does Monet need?

No credential environment variables were found in its source, so it appears to need none.

How current is this page?

The grade is for one exact copy of the source (f7106a4f5f53), read on 2026-10-07. The repository is watched and re-audited when it changes.

Advertisement