Sandbox
@7836246/claude-team-mcp

MCP server for multi-agent development teams

Claude Team is an MCP server that plugs into Claude Code, Cursor, and Windsurf so your agent can coordinate multiple models as a team. It includes task delegation, workflow templates, code review, bug fixing, observability, and collaboration history.

49 starsโ€ข6 forksโ€ขTypeScriptโ€ขUpdated 5mo ago
Who it's for

Builders who use Claude Code, Cursor, or Windsurf and want their agent to route work across multiple models and experts.

What it delivers

You can turn one agent session into a multi-model workflow with planning, review, and history instead of handling every step yourself.

What it does

Multi-model collaboration

Coordinates GPT, Claude, Gemini, and custom workers on the same task.

Smart task distribution

Uses a tech-lead step to break work apart and assign it to the best-fit experts.

Workflow templates

Provides prebuilt flows for code generation, bug fixing, refactoring, review, and documentation.

Custom experts

Lets you define experts like Rust, K8s, or Security with environment variables.

Observability tools

Shows team status, cost estimates, and task plans before work runs.

History tools

Keeps collaboration records you can list, inspect, search, and reuse.

How to get it

  1. 1Run
    # Global install
    npm install -g claude-team
    
    # Or use directly with npx (no install needed)
    npx claude-team
  2. 2Run
    > Help me build a user login feature with the team
    
    > Have the team optimize this code for performance

README

๐Ÿค– Claude Team

Multi-Agent MCP Server for AI-Powered Development Teams

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

npm version downloads Node.js MCP License Tests

English | ็ฎ€ไฝ“ไธญๆ–‡


โœจ Features

FeatureDescription
๐Ÿค– Multi-Model CollaborationConfigure multiple AI models to work together, each leveraging their strengths
๐Ÿง  Smart Task DistributionTech Lead analyzes tasks and automatically assigns them to the best-suited experts
๐Ÿ”— Workflow Templates5 pre-built workflows: code generation, bug fixing, refactoring, review, documentation
๐ŸŽฏ Custom ExpertsDefine your own experts (Rust, K8s, Security, etc.) via environment variables
๐Ÿ“Š ObservabilityDashboard, cost estimation, and task planning preview
๐ŸŒ Proxy API SupportCustom Base URLs, compatible with various proxy services
๐Ÿ“ Collaboration HistoryComplete record of all collaborations with search support

๐Ÿš€ 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:

๐Ÿ“ Configuration File Locations
IDEPath
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

๐ŸŽฌ How It Works

User: "Optimize this SQL query for performance"

Tech Lead Analysis โ†’
โ”œโ”€โ”€ Creates: SQL Optimization Expert (powerful)
โ”œโ”€โ”€ Creates: Index Analysis Expert (balanced)  
โ””โ”€โ”€ Workflow: sequential
User: "Build a settings page with dark mode"

Tech Lead Analysis โ†’
โ”œโ”€โ”€ Creates: UI Component Expert (balanced)
โ”œโ”€โ”€ Creates: Theme System Expert (fast)
โ”œโ”€โ”€ Creates: State Management Expert (balanced)
โ””โ”€โ”€ Workflow: parallel โ†’ review

๐Ÿ› ๏ธ Available Tools

Core Tools

ToolDescription
team_work๐Ÿš€ Team collaboration (auto-creates experts)
ask_expert๐Ÿ’ฌ Consult an expert (supports custom experts)
code_review๐Ÿ” Code review
fix_bug๐Ÿ› Bug fixing

Workflow Tools

ToolDescription
list_workflows๐Ÿ“‹ List all workflow templates
run_workflowโ–ถ๏ธ Execute a specific workflow
suggest_workflow๐Ÿ’ก Auto-recommend workflow based on task

Pre-built Workflows:

WorkflowPurposeSteps
code-generationGenerate code from requirementsDesign โ†’ Implement โ†’ Test โ†’ Review
bug-fixDiagnose and fix bugsDiagnose โ†’ Fix โ†’ Verify
refactoringCode refactoringAnalyze โ†’ Plan โ†’ Execute โ†’ Review
code-reviewMulti-dimensional reviewSecurity / Quality / Performance (parallel)
documentationGenerate documentationAnalyze โ†’ Document

Observability Tools

ToolDescription
team_dashboard๐ŸŽ›๏ธ View team status, experts, models, stats
cost_estimate๐Ÿ’ฐ Estimate task cost (tokens, price, time)
explain_plan๐Ÿง  Preview task assignment plan
usage_stats๐Ÿ“ˆ View model usage statistics

Integration Tools

ToolDescription
read_project_files๐Ÿ“„ Read project files for context
analyze_project_structure๐Ÿ—๏ธ Analyze project structure and tech stack
generate_commit_message๐Ÿ“ Generate commit message from diff

History Tools

ToolDescription
history_list๐Ÿ“‹ View collaboration history
history_get๐Ÿ“„ Get history details
history_search๐Ÿ”Ž Search history records
history_context๐Ÿ“š Get recent context

โš™๏ธ Configuration

Environment Variables

VariableRequiredDescription
CLAUDE_TEAM_MAIN_KEYโœ…Main model API Key
CLAUDE_TEAM_MAIN_URLโŒMain model API URL
CLAUDE_TEAM_MAIN_MODELโŒMain model ID (default: gpt-4o)
CLAUDE_TEAM_MAIN_PROVIDERโŒProvider: openai / anthropic / gemini
CLAUDE_TEAM_MODEL{N}_*โŒWorker model N config (inherits from MAIN)
CLAUDE_TEAM_CUSTOM_EXPERTSโŒCustom 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\"}}"
  }
}
FieldRequiredDescription
nameโœ…Expert display name
promptโœ…Expert role description (System Prompt)
tierโŒModel tier: fast / balanced / powerful
skillsโŒSkill tags array

Model Tiers

TierUse CaseExample Scenarios
fastSimple, quick tasksFormatting, simple queries, docs
balancedRegular dev tasksComponents, APIs, unit tests
powerfulComplex reasoningArchitecture, optimization, security

๐Ÿ“ฆ Changelog

v0.4.0

  • ๐ŸŽฏ Custom Experts - Define experts via environment variables
  • ๐Ÿ”— Workflow Templates - 5 pre-built workflows
  • ๐Ÿ“Š Observability - Dashboard, cost estimation, plan preview
  • ๐Ÿ”Œ Integration - Project file reading, structure analysis, commit messages
  • ๐Ÿ’ก Smart Recommendations - Auto-suggest workflows
  • ๐Ÿงช Test Coverage - 155 test cases

v0.3.0

  • ๐Ÿ”„ Task interrupt/resume support
  • ๐Ÿ’ฌ Multi-turn expert conversations
  • ๐Ÿ“Š Token counting and cost estimation
  • ๐Ÿ“‹ Expert templates (6 built-in + custom)
  • ๐Ÿ”” Webhook notifications
  • โšก Exponential backoff retry
  • ๐Ÿ”ง Hot config reload
Earlier versions

v0.2.x

  • ๐ŸŒŠ Streaming output support
  • ๐Ÿ“Š Usage statistics
  • ๐ŸŽฏ Model strategies
  • ๐Ÿ’พ Result caching
  • ๐Ÿ”„ Auto model switching

v0.1.x

  • ๐ŸŽ‰ Initial release
  • ๐Ÿค– Multi-model collaboration
  • ๐ŸŒ Proxy API support

๐Ÿค Contributing

Contributions are welcome! Please read our:

๐Ÿ“„ License

MIT


โญ Star History

Star History Chart


โฌ† Back to Top

Made with โค๏ธ by the community

Files in the repo

Repository payloadโ€ข15 top-level entries
  • .github
  • src
  • .gitignore
  • .npmignore
  • CHANGELOG.md
  • CODE_OF_CONDUCT.md
  • CONTRIBUTING.md
  • eslint.config.js
  • LICENSE
  • package-lock.json
  • package.json
  • README_CN.md
  • README.md
  • SECURITY.md
  • tsconfig.json

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More connectors

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph โ€” average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

43k

Universal provider proxy for OpenAI Codex & Claude Code โ€” use any LLM (Claude, Gemini, Grok, DeepSeek, Ollamaโ€ฆ) with Codex CLI, App, SDK, and Claude Code

14k
okf-memory/
okf-agent-memory

Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300ยตs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.

547
tirth8205/
code-review-graph

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

31k
2akouwu/
reverify

Stop your AI from making things up โ€” it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.

1.1k
t8y2/dbxConnectors

20 MB lightweight cross-platform database client for 90+ databases, including MySQL, PostgreSQL, SQLite, Redis, MongoDB, DuckDB, SQL Server, and Dameng. Built-in AI, MCP Server, CLI, desktop and Docker. | ่ฝป้‡็บง่ทจๅนณๅฐๆ•ฐๆฎๅบ“็ฎก็†ๅทฅๅ…ท๏ผŒๆ”ฏๆŒ MySQLใ€PostgreSQLใ€SQLiteใ€Redisใ€MongoDBใ€่พพๆขฆ็ญ‰ 90+ ๆ•ฐๆฎๅบ“๏ผŒๆไพ›ๆกŒ้ข็ซฏใ€Dockerใ€CLIใ€ๅ†…็ฝฎ AI ๅŠฉๆ‰‹ๅ’Œ MCP Serverใ€‚

19k