How do I install Claude Team MCP?

Run npx claude-team-mcp, then add the server to your MCP client's configuration. Conduid has recorded 0 installs, so the command is known to work with current clients.

Is Claude Team MCP safe to use with an AI agent?

Its trust score is 61 out of 100 (good). It passes 0 of 1 static security checks; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Claude Team MCP still maintained?

The last commit was 8 months ago, with 0 open issues. That's long enough that you should check whether the maintainer is responding to issues before depending on it.

About Claude Team MCP

Claude Team MCP is an MCP server published by 7836246 in the Developer Tools category: 🤖 Multi-Agent MCP Server - Let Claude Code / Windsurf / Cursor orchestrate GPT, Claude, Gemini to work as an AI dev team. It has been installed 0 times through Conduid.

The repository has 44 stars and 6 forks, with the last commit 8 months ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues (0) before depending on it in production.

Install

npx claude-team-mcp

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Claude Team MCP

I know everything about Claude Team MCP. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

·README presentNot checked yet.
·License declaredNot checked yet.
·Tests presentNot checked yet.
·Dependencies pinnedNot checked yet.
·No dynamic code executionNot checked yet.
!Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.

Releases

v0.4.0v0.4.0 - 自定义专家、工作流模板、可观测性工具 · 21 Dec 2025🎉 v0.4.0 新功能 🎯 自定义专家通过环境变量 `CLAUDE_TEAM_CUSTOM_EXPERTS` 定义自己的专家 🔗 工作流模板 5 个预定义工作流：code-generation、bug-fix、refactoring、code-review、documentation 📊 可观测性工具 team_dashboard - 查看团队状态 cost_estimate - 预估任务成本 explain_plan - 预览任务分配方案 🔌 项目集成…

v0.3.0v0.3.0 · 20 Dec 2025🎉 v0.3.0 新功能核心功能 🔄 **任务中断/恢复** - 长任务中断后可从历史恢复继续执行 💬 **专家多轮对话** - 支持与特定专家进行多轮对话 📊 **Token 计数** - 统计 token 使用量和估算 API 成本 📋 **专家模板** - 6 个内置模板 + 自定义模板管理 🔔 **Webhook 通知** - 任务完成后发送通知改进 ⚡ **指数退避** - 智能重试和 429 速率限制处理 🔧 **配置热重载** - 支持不重启更新配置 ✅…

v0.2.3v0.2.3 - 模型格式配置 · 20 Dec 2025✨ 新功能 🎛️ PROVIDER 配置支持为每个模型指定响应格式，适配不同中转服务： { "CLAUDE_TEAM_MAIN_PROVIDER": "openai", "CLAUDE_TEAM_MODEL1_PROVIDER": "anthropic", "CLAUDE_TEAM_MODEL2_PROVIDER": "gemini" } 可选值 `openai` - OpenAI 格式（默认） `anthropic` - Claude 格式 `gemini` -…

v0.2.2v0.2.2 - 流式输出支持 · 20 Dec 2025✨ 新功能 🌊 流式输出所有模型适配器现已支持流式输出： OpenAI** - GPT 系列及兼容 API Claude** - Anthropic Claude 系列 Gemini** - Google Gemini 系列使用方式适配器提供 `stream()` 方法，返回 AsyncGenerator： for await (const chunk of adapter.stream(messages)) {…

v0.2.1v0.2.1 - 使用统计 · 20 Dec 2025✨ 新功能 📊 使用统计新增 `usage_stats` 工具，可查看：总调用次数成功/失败次数各模型调用统计平均耗时、最短/最长耗时使用方法直接调用 `usage_stats` 工具即可查看统计信息。安装 npx claude-team

README

🤖 Claude Team

Multi-Agent MCP Server for AI-Powered Development Teams

Orchestrate GPT, Claude, Gemini and more to collaborate on complex tasks

English | 简体中文

✨ Features

Feature	Description
🤖 Multi-Model Collaboration	Configure multiple AI models to work together, each leveraging their strengths
🧠 Smart Task Distribution	Tech Lead analyzes tasks and automatically assigns them to the best-suited experts
🔗 Workflow Templates	5 pre-built workflows: code generation, bug fixing, refactoring, review, documentation
🎯 Custom Experts	Define your own experts (Rust, K8s, Security, etc.) via environment variables
📊 Observability	Dashboard, cost estimation, and task planning preview
🌐 Proxy API Support	Custom Base URLs, compatible with various proxy services
📝 Collaboration History	Complete record of all collaborations with search support

🚀 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:

IDE	Path
Claude Code	`~/.claude/config.json`
Windsurf	`~/.codeium/windsurf/mcp_config.json`
Cursor	`~/.cursor/mcp.json`

{
  "mcpServers": {
    "claude-team": {
      "command": "npx",
      "args": ["-y", "claude-team"],
      "env": {
        "CLAUDE_TEAM_MAIN_KEY": "sk-your-api-key",
        "CLAUDE_TEAM_MAIN_URL": "https://api.openai.com/v1",
        "CLAUDE_TEAM_MAIN_MODEL": "gpt-4o",
        "CLAUDE_TEAM_MAIN_PROVIDER": "openai"
      }
    }
  }
}

Start Using

> Help me build a user login feature with the team

> Have the team optimize this code for performance

🎬 How It Works

User: "Optimize this SQL query for performance"

Tech Lead Analysis →
├── Creates: SQL Optimization Expert (powerful)
├── Creates: Index Analysis Expert (balanced)  
└── Workflow: sequential

User: "Build a settings page with dark mode"

Tech Lead Analysis →
├── Creates: UI Component Expert (balanced)
├── Creates: Theme System Expert (fast)
├── Creates: State Management Expert (balanced)
└── Workflow: parallel → review

🛠️ Available Tools

Core Tools

Tool	Description
`team_work`	🚀 Team collaboration (auto-creates experts)
`ask_expert`	💬 Consult an expert (supports custom experts)
`code_review`	🔍 Code review
`fix_bug`	🐛 Bug fixing

Workflow Tools

Tool	Description
`list_workflows`	📋 List all workflow templates
`run_workflow`	▶️ Execute a specific workflow
`suggest_workflow`	💡 Auto-recommend workflow based on task

Pre-built Workflows:

Workflow	Purpose	Steps
`code-generation`	Generate code from requirements	Design → Implement → Test → Review
`bug-fix`	Diagnose and fix bugs	Diagnose → Fix → Verify
`refactoring`	Code refactoring	Analyze → Plan → Execute → Review
`code-review`	Multi-dimensional review	Security / Quality / Performance (parallel)
`documentation`	Generate documentation	Analyze → Document

Observability Tools

Tool	Description
`team_dashboard`	🎛️ View team status, experts, models, stats
`cost_estimate`	💰 Estimate task cost (tokens, price, time)
`explain_plan`	🧠 Preview task assignment plan
`usage_stats`	📈 View model usage statistics

Integration Tools

Tool	Description
`read_project_files`	📄 Read project files for context
`analyze_project_structure`	🏗️ Analyze project structure and tech stack
`generate_commit_message`	📝 Generate commit message from diff

History Tools

Tool	Description
`history_list`	📋 View collaboration history
`history_get`	📄 Get history details
`history_search`	🔎 Search history records
`history_context`	📚 Get recent context

⚙️ Configuration

Environment Variables

Variable	Required	Description
`CLAUDE_TEAM_MAIN_KEY`	✅	Main model API Key
`CLAUDE_TEAM_MAIN_URL`	❌	Main model API URL
`CLAUDE_TEAM_MAIN_MODEL`	❌	Main model ID (default: gpt-4o)
`CLAUDE_TEAM_MAIN_PROVIDER`	❌	Provider: `openai` / `anthropic` / `gemini`
`CLAUDE_TEAM_MODEL{N}_*`	❌	Worker model N config (inherits from MAIN)
`CLAUDE_TEAM_CUSTOM_EXPERTS`	❌	Custom experts (JSON format)

N = 1, 2, 3... supports up to 10 worker models

Custom Experts

Define your own experts beyond the built-in frontend, backend, qa:

{
  "env": {
    "CLAUDE_TEAM_CUSTOM_EXPERTS": "{\"rust\":{\"name\":\"Rust Expert\",\"prompt\":\"You are a Rust expert...\",\"tier\":\"powerful\"},\"k8s\":{\"name\":\"K8s Expert\",\"prompt\":\"You are a Kubernetes expert...\",\"tier\":\"balanced\"}}"
  }
}

Field	Required	Description
`name`	✅	Expert display name
`prompt`	✅	Expert role description (System Prompt)
`tier`	❌	Model tier: `fast` / `balanced` / `powerful`
`skills`	❌	Skill tags array

Model Tiers

Tier	Use Case	Example Scenarios
`fast`	Simple, quick tasks	Formatting, simple queries, docs
`balanced`	Regular dev tasks	Components, APIs, unit tests
`powerful`	Complex reasoning	Architecture, optimization, security

📦 Changelog

v0.4.0

🎯 Custom Experts - Define experts via environment variables
🔗 Workflow Templates - 5 pre-built workflows
📊 Observability - Dashboard, cost estimation, plan preview
🔌 Integration - Project file reading, structure analysis, commit messages
💡 Smart Recommendations - Auto-suggest workflows
🧪 Test Coverage - 155 test cases

v0.3.0

🔄 Task interrupt/resume support
💬 Multi-turn expert conversations
📊 Token counting and cost estimation
📋 Expert templates (6 built-in + custom)
🔔 Webhook notifications
⚡ Exponential backoff retry
🔧 Hot config reload

v0.2.x

🌊 Streaming output support
📊 Usage statistics
🎯 Model strategies
💾 Result caching
🔄 Auto model switching

v0.1.x

🎉 Initial release
🤖 Multi-model collaboration
🌐 Proxy API support

🤝 Contributing

Contributions are welcome! Please read our:

📄 License

MIT

⭐ Star History

⬆ Back to Top

Made with ❤️ by the community

Read full README

README mirrored from the source repository 19 days ago. The original is authoritative.

About Claude Team MCP

Install

Ask AI

Security checks

Releases

README

🤖 Claude Team

✨ Features

🚀 Quick Start

Installation

Basic Configuration

Start Using

🎬 How It Works

🛠️ Available Tools

Core Tools

Workflow Tools

Observability Tools

Integration Tools

History Tools

⚙️ Configuration

Environment Variables

Custom Experts

Model Tiers

📦 Changelog

v0.4.0

v0.3.0

v0.2.x

v0.1.x

🤝 Contributing

📄 License

⭐ Star History

Alternatives to Claude Team MCP

oraios/serena

For Beginners

antv/mcp-server-chart

Harbor

Skills

Agents

About Claude Team MCP