Claude TeamSAFE
🤖 Multi-Agent MCP Server - Let Claude Code / Windsurf / Cursor orchestrate GPT, Claude, Gemini to work as an AI dev team
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Multi-Agent MCP Server for AI-Powered Development Teams
Orchestrate GPT, Claude, Gemini and more to collaborate on complex tasks
[](https://www.npmjs.com/package/claude-team) [](https://www.npmjs.com/package/claude-team) [](https://nodejs.org/) [](https://modelcontextprotocol.io) [](LICENSE) [](https://github.com/7836246/claude-team-mcp)
English | 简体中文
✨ Features
🚀 Quick Start
Installation
# Global install npm install -g claude-team # Or use directly with npx (no install needed) npx claude-team
Basic Configuration
Add to your IDE's MCP configuration file:
📍 Configuration File
443bd1d6391eOBSERVED · 2026-10-08Connect
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 claude-team --env ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY} --env CLAUDE_TEAM_API_KEY=${CLAUDE_TEAM_API_KEY} --env CLAUDE_TEAM_MAIN_KEY=${CLAUDE_TEAM_MAIN_KEY} --env GEMINI_API_KEY=${GEMINI_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"claude-team": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"CLAUDE_TEAM_API_KEY": "${CLAUDE_TEAM_API_KEY}",
"CLAUDE_TEAM_MAIN_KEY": "${CLAUDE_TEAM_MAIN_KEY}",
"GEMINI_API_KEY": "${GEMINI_API_KEY}"
}
}
}
}Exposed tools (25)
23 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
analyze_project_structure | read | 分析项目结构,识别技术栈和架构 |
ask_expert | read | 向特定专家咨询问题 |
code_review | read | 让专家审查代码 |
cost_estimate | read | 预估任务执行成本(Token 用量、预计耗时) |
explain_plan | read | 解释 Tech Lead 会如何分配任务(不实际执行) |
fix_bug | read | 让 QA 专家修复 Bug |
generate_commit_message | write | 根据代码变更生成 Git commit message |
history_context | read | 获取最近的协作上下文,可用于继续之前的工作 |
history_get | read | 获取某次协作的详细记录 |
history_list | read | 查看团队协作历史记录列表 |
history_search | read | 搜索协作历史记录 |
list_workflows | read | 列出所有可用的工作流模板 |
read_project_files | read | 读取项目文件内容,让专家了解代码上下文 |
run_workflow | write | 使用指定工作流执行任务 |
suggest_workflow | read | 根据任务自动推荐合适的工作流 |
team_dashboard | read | 查看团队当前状态:可用专家、模型配置、最近活动 |
team_work | read | 让 AI 开发团队协作完成任务。团队包含前端专家、后端专家、QA专家,会智能分配任务并互相协作。 |
usage_stats | read | 查看各模型的使用统计(调用次数、成功率、平均耗时) |
代码审查工作流 | read | 多维度代码审查流程 |
代码生成工作流 | read | 用于从需求生成代码的标准流程 |
代码重构工作流 | read | 用于代码重构的标准流程 |
我的工作流 | read | 自定义工作流 |
文档生成工作流 | read | 自动生成技术文档 |
自定义 | read | 自定义工作流 |
自定义代码生成 | read | 自定义的代码生成流程 |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
return createHash('md5').update(normalized).digest('hex');@anthropic-ai/sdk, @google/generative-ai, @modelcontextprotocol/sdk, openai, p-limit, yaml, zod, @eslint/js
Gates applied: no_behavioural_pass.
443bd1d6391efull audit observations/trust-audit/mcp-server/7836246__claude-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 |
|---|---|---|---|---|---|
| 2026-10-08 | 443bd1d6391e | SAFE | B | 89 | first audit |
Questions
What is the Claude Team MCP server?
🤖 Multi-Agent MCP Server - Let Claude Code / Windsurf / Cursor orchestrate GPT, Claude, Gemini to work as an AI dev team
What tools does Claude Team expose?
25 in total: 23 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Claude Team safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Claude Team need?
It reads ANTHROPIC_API_KEY, CLAUDE_TEAM_API_KEY, CLAUDE_TEAM_MAIN_KEY, GEMINI_API_KEY and OPENAI_API_KEY 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 Claude Team run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as claude-team at 0.4.1.
How current is this page?
The grade is for one exact copy of the source (443bd1d6391e), read on 2026-10-08. The repository is watched and re-audited when it changes.