Agentcrew
Chat application with multi-agents system supports multi-models and MCP
What is Agentcrew?
Agentcrew is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to chat application with multi-agents system supports multi-models and mcp
Chat application with multi-agents system supports multi-models and MCP
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Chat application with multi-agents system supports multi-mod
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx agentcrewConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Agentcrew
AgentCrew is a multi-agent chat platform that supports Claude, GPT-4, Gemini, and any OpenAI-compatible endpoint, with full Model Context Protocol (MCP) integration so agents can use external tools alongside built-in capabilities like code execution, web search, shell commands, and conversation memory. It runs as a desktop GUI, terminal console, or HTTP API server, making it suitable for both interactive development sessions and automated agent pipelines. AgentCrew is the MCP client here — it connects to your existing MCP servers and lets multiple specialized agents collaborate on complex tasks.
Prerequisites
- Python 3.12 or higher installed
- API key for at least one supported LLM provider: ANTHROPIC_API_KEY, OPENAI_API_KEY, or GEMINI_API_KEY
- pip or the automated installer script (curl-based for macOS/Linux)
- Optional: ElevenLabs or DeepInfra API key for voice features
Install AgentCrew
Install AgentCrew using pip. Alternatively, use the one-line installer for macOS/Linux which sets up the binary on your PATH automatically.
pip install agentcrew-aiSet your LLM provider API key
Export the API key for your primary LLM provider as an environment variable. AgentCrew supports multiple providers simultaneously — set whichever keys you have.
export ANTHROPIC_API_KEY=sk-ant-your-key-here
export OPENAI_API_KEY=sk-your-openai-key-here
export GEMINI_API_KEY=your-gemini-key-hereLaunch the desktop chat interface
Start AgentCrew in its default desktop GUI mode. The interface lets you select your model, configure agents, and start multi-agent conversations.
agentcrew chatOr launch in terminal console mode
For a terminal-only experience without the GUI, use the --console flag. This is useful for remote servers or scripted workflows.
agentcrew chat --consoleConnect MCP servers to your agents
AgentCrew can connect to any MCP server. Edit the configuration at ~/.AgentCrew/config.json to add MCP server entries. Each agent in your crew can be given access to specific MCP tools.
{
"mcp_servers": {
"filesystem": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/tmp"]
}
},
"providers": {
"anthropic": {
"api_key": "sk-ant-your-key-here"
}
}
}Define a multi-agent crew
Configure specialized agents in config.json. Agents can hand off tasks to each other, share conversation context, and use different LLM models for different roles.
Agentcrew Examples
Client configuration
AgentCrew config.json showing MCP server integration and API key configuration.
{
"mcp_servers": {
"filesystem": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/workspace"]
},
"web-search": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-brave-search"],
"env": { "BRAVE_API_KEY": "your-brave-key" }
}
},
"providers": {
"anthropic": { "api_key": "sk-ant-your-key-here" },
"openai": { "api_key": "sk-your-openai-key-here" }
}
}Prompts to try
Example prompts that take advantage of AgentCrew's multi-agent and MCP capabilities.
- "Research the latest developments in quantum computing and write a summary report"
- "Analyze this Python codebase and have one agent identify bugs while another suggests refactors"
- "Use the web search agent to find recent pricing for AWS Lambda and compile a cost comparison"
- "Run the test suite in /workspace/tests and have an agent fix any failing tests"
- "Delegate the data analysis to one agent and report writing to another, then combine their outputs"
- "Set up a recurring agent that monitors a directory for new CSV files and processes each one"Troubleshooting Agentcrew
agentcrew command not found after pip install
The binary may not be on your PATH. Try `python -m agentcrew` as an alternative, or check if the pip scripts directory is in your PATH. On macOS/Linux, use the official installer instead: `curl -LsSf https://agentcrew.dev/install.sh | bash`.
MCP server tools are not available to agents
Verify your MCP server entries in ~/.AgentCrew/config.json use the correct command and args. Test that the MCP server command works independently in your terminal. Restart AgentCrew after editing the config file.
API key errors when switching between LLM providers
Each provider requires its own API key set in config.json under the providers section or as environment variables (ANTHROPIC_API_KEY, OPENAI_API_KEY, GEMINI_API_KEY). Make sure you have a valid key for each model you select in the agent configuration.
Frequently Asked Questions about Agentcrew
What is Agentcrew?
Agentcrew is a Model Context Protocol (MCP) server that chat application with multi-agents system supports multi-models and mcp It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Agentcrew?
Follow the installation instructions on the Agentcrew GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Agentcrew?
Agentcrew works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Agentcrew free to use?
Yes, Agentcrew is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Agentcrew Alternatives — Similar Coding Agents Servers
Looking for alternatives to Agentcrew? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Agentcrew in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Agentcrew?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.