AI Agent TeamBLOCK
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。一键安装,支持中英文命令,大幅提升开发效率!
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
💛 Sponsored by DolOffer — GPT & Claude 正版会员充值,输入优惠码 AI8888 享9折特惠
🚀 拥有24/7专业AI开发团队:产品经理、全栈开发、前端开发、后端开发、测试工程师、DevOps工程师、技术负责人
💾 Thread Manager 让 AI 拥有记忆! 语义搜索 | 任务线程管理 | 完整上下文恢复 | 自动 Git 版本控制
⚡ 只需 3 步完成安装 → 马上开始使用!
Agent Skills(独立安装)
这些 Skill 已发布为独立仓库,可通过 skills install 命令安装到任意项目中:
兼容 Claude Code / Cursor / Codex CLI / Gemini CLI / Windsurf 等 50+ 运行时。
🚀 快速开始
✨ 核心特性
- 🎯 **八大
6ea3a1777623OBSERVED · 2026-10-01Connect
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. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add ai-agent-team --env GITHUB_TOKEN=${GITHUB_TOKEN} -- npx -y [email protected]{
"mcpServers": {
"ai-agent-team": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"GITHUB_TOKEN": "${GITHUB_TOKEN}"
}
}
}
}Exposed tools (21)
17 read · 3 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
API接口模块 | read | 提供RESTful API接口供前端调用 |
add_message | write | Add a message to the current active thread. Use this to record conversation messages. |
create_thread | write | Create a new conversation thread to isolate context for a specific task. |
delete_thread | destructive | Delete a thread and all associated data permanently. |
get_current_thread | read | Get information about the currently active thread. |
get_thread | read | Get detailed information about a specific thread, optionally including messages and file changes. |
list_threads | read | List all conversation threads with filtering and sorting options. |
search_messages | read | Semantically searches for relevant messages in the conversation history based on a natural language query. |
switch_thread | read | Switch the active context to a specific thread. |
track_file_change | read | Record a file change event for the current active thread. If stats are not provided, they will be auto-detected from git. |
update_thread | write | Update the metadata (title, description, tags) of a thread. |
业务逻辑模块 | read | 处理核心业务逻辑,实现系统的核心功能 |
报表统计模块 | read | 生成各类统计报表和数据可视化图表 |
数据处理模块 | read | 负责数据的增删改查和业务逻辑处理 |
数据访问模块 | read | 负责数据的存储、检索和管理,确保数据的一致性和完整性 |
文件管理模块 | read | 处理文件上传、下载和存储功能 |
日志监控模块 | read | 记录系统运行日志,提供系统监控和性能分析功能 |
消息通知模块 | read | 实现系统消息推送和邮件通知功能 |
用户界面模块 | read | 负责用户交互和界面展示,提供直观友好的操作界面 |
用户管理模块 | read | 实现用户注册、登录、权限管理等功能 |
系统配置模块 | read | 管理系统配置和参数设置,支持动态配置和热更新 |
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.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (6 observation(s))
- Network
- declared (8 observation(s))
- Shell
- declared (7 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (19)
return yaml.load(content);
const child = exec(`${command} "${htmlPath}"`, (error) => {delete_thread
.changelogrc.json
{{{prLink this ../../../config.template.prUrl}}}{{{prLink this ../../../config.template.prUrl}}}const ChangelogGenerator = require('../../src/core/ChangelogGenerator');const CommitClassifier = require('../../src/core/CommitClassifier');const GitAnalyzer = require('../../src/core/GitAnalyzer');@octokit/rest, chalk, commander, conventional-commits-parser, dotenv, handlebars, inquirer, js-yaml
playwright
pdfkit, pdfkit-table, glob, commander, chalk, inquirer, fs-extra, path
@modelcontextprotocol/sdk, @xenova/transformers, better-sqlite3, date-fns, fs-extra, simple-git, uuid, zod
fs-extra, glob, semver, commander
.claude/skills/thread-manager/models/Xenova/all-MiniLM-L6-v2/onnx/model_quantized.onnx
drawnote_20251111_172200_2x2.png
drawnote_ai_agent_team_v1.0.2.png
examples/softcopyright.gif
examples/tidymydesktop.png
Gates applied: no_behavioural_pass.
6ea3a1777623full audit observations/trust-audit/mcp-server/peterfei__ai-agent-team.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-01 | 6ea3a1777623 | BLOCK | D | 69 | first audit |
Questions
What is the AI Agent Team MCP server?
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。一键安装,支持中英文命令,大幅提升开发效率!
What tools does AI Agent Team expose?
21 in total: 17 read-only, 3 that write, and 1 that can delete or overwrite (delete_thread). Every one is listed on this page with its risk.
Is AI Agent Team safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 2 critical or high issues in the source. Each one is listed on this page with the file and line it is on. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does AI Agent Team need?
It reads GITHUB_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does AI Agent Team run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as ai-agent-team at 2.1.0.
How current is this page?
The grade is for one exact copy of the source (6ea3a1777623), read on 2026-10-01. The repository is watched and re-audited when it changes.