Ai Agent Team MCP Server
ai-agent-team
npm
v2.1.0
Published by peterfei — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
AI Agent Team - 拥有24/7专业AI开发团队：产品经理、前端开发、后端开发、测试工程师、DevOps工程师、技术负责人。全新Thread Manager让AI拥有记忆！支持任务线程管理、自动Git版本控制、完整上下文恢复。一键安装，开发效率飙升200%！集成drawnote、tidymydesktop、softcopyright、changelog-generator和thread-manager五大智能Skill。
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 1.2 = 99. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −1.2 | Package runs install-time scripts MTC-SUP-010 | supply-chain |
2. Client adoption risk — 99 − 7 = 92. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 10
high Shell/command execution in server code (bin/ai-agent-team.js)MTC-SRC-002
In the server's implementation (`bin/ai-agent-team.js:11`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: spawnSync } = require('child_process'); const readline = require('readline'); // 颜色输出 const colors = { reset: '\x1b[
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server bin/ai-agent-team.js
medium Dynamic module load from a non-literal (.claude/skills/changelog-generator/src/utils/ConfigLoader.js)MTC-SRC-005
In the server's implementation (`.claude/skills/changelog-generator/src/utils/ConfigLoader.js:66`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: = '.js') { return require(configPath); } throw new Error(`Unsupported config file format: ${ext}`); }
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server .claude/skills/changelog-generator/src/utils/ConfigLoader.js
low Shell/command execution in packaging/dev tooling (.claude/skills/drawnote/scripts/install-dependencies.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`.claude/skills/drawnote/scripts/install-dependencies.js:8`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: st { spawn } = require('child_process'); const fs = require('fs'); const path = require('path'); console.log('🎭 DrawNo
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server .claude/skills/drawnote/scripts/install-dependencies.js
low Shell/command execution in packaging/dev tooling (.claude/skills/drawnote/scripts/verify-installation.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`.claude/skills/drawnote/scripts/verify-installation.js:10`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: , execSync } = require('child_process'); console.log('🔍 DrawNote Skill 安装验证工具'); console.log('========================
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server .claude/skills/drawnote/scripts/verify-installation.js
low Shell/command execution in packaging/dev tooling (.claude/skills/softcopyright/scripts/auto-print-pdf.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`.claude/skills/softcopyright/scripts/auto-print-pdf.js:6`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: nst { exec } = require('child_process'); const fs = require('fs-extra'); const path = require('path'); const chalk = req
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server .claude/skills/softcopyright/scripts/auto-print-pdf.js
low Shell/command execution in packaging/dev tooling (.claude/skills/softcopyright/scripts/simple-pdf-generator.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`.claude/skills/softcopyright/scripts/simple-pdf-generator.js:10`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execSync } = require('child_process'); /** * 生成软件说明书PDF * @param {Object} projectInfo 项目信息 * @param {string} outpu
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server .claude/skills/softcopyright/scripts/simple-pdf-generator.js
low Shell/command execution in packaging/dev tooling (.claude/skills/softcopyright/scripts/system-chrome-pdf.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`.claude/skills/softcopyright/scripts/system-chrome-pdf.js:6`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execSync } = require('child_process'); const fs = require('fs-extra'); const path = require('path'); const chalk = req
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server .claude/skills/softcopyright/scripts/system-chrome-pdf.js
low Shell/command execution in packaging/dev tooling (.claude/skills/tidymydesktop/scripts/run.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`.claude/skills/tidymydesktop/scripts/run.js:8`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: st { spawn } = require('child_process'); const path = require('path'); const os = require('os'); // 检查 Node.js 版本 const
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server .claude/skills/tidymydesktop/scripts/run.js
low Shell/command execution in packaging/dev tooling (scripts/preinstall.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/preinstall.js:8`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execSync } = require('child_process'); const path = require('path'); console.log('🔍 AI Agent Team - 安装前检查...'); //
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server scripts/preinstall.js
low Package runs install-time scripts (preinstall, postinstall)MTC-SUP-010
"ai-agent-team" executes preinstall/postinstall script(s) at install time. An install hook runs at install time; most are routine build/setup, but review what it does before trusting it.
Evidence: node scripts/preinstall.js ; node scripts/postinstall.js
Fix: Review the scripts; install with --ignore-scripts where possible and vet what they do.
Location: package ai-agent-team
What this scan could not see
- No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Versions 1
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v2.1.0 latest |
A 92/100 | 10 | 1.13.0 | 2026-09-07 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan ai-agent-team --onlineMore in Productivity & Workflow
MCP AgentChat - 让 AI Agent 通过 Telegram 与用户实时交互：发送消息、图片，等待用户回复
A Model Context Protocol (MCP) server for Airthings Air Quality Monitor devices.
MCP server for Anki
TypeScript package for reading and searching Apple Notes on macOS via direct SQLite access. Includes markdown conversion, attachment support, and offers a local MCP server!
Verified biotech catalyst calendar (PDUFA/AdComm/trial readouts) anchored to official sources.
Appointment booking platform letting agents check provider availability and create bookings.