Autoteam Orchestration
Orchestrate AI agents with YAML-driven workflows via universal Model Context Protocol (MCP)
What is Autoteam Orchestration?
Autoteam Orchestration is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to orchestrate ai agents with yaml-driven workflows via universal model context protocol (mcp)
Orchestrate AI agents with YAML-driven workflows via universal Model Context Protocol (MCP)
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Orchestrate AI agents with YAML-driven workflows via univers
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx autoteamConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Autoteam Orchestration
Autoteam is a YAML-driven AI agent orchestration platform that exposes its control plane through the Model Context Protocol, allowing AI clients to manage and coordinate multi-agent workflows across providers including Claude, ChatGPT, Gemini, and GitHub. It deploys as a containerized service (Docker/Podman) and supports pluggable MCP servers for GitHub, Slack, databases, and filesystems, enabling teams to build complex automated workflows — code reviews, PR management, data pipelines — defined entirely in YAML and orchestrated through natural-language prompts.
Prerequisites
- Docker 20.10 or later, or Podman 3.0 or later
- Minimum 4 GB RAM (8 GB recommended)
- Linux, macOS, or Windows with WSL2
- API keys for the AI providers you plan to use (Anthropic, OpenAI, Google, etc.)
- An MCP-compatible client to interact with the control plane
Install Autoteam using the install script
Run the one-line install script to download and install the autoteam binary.
curl -fsSL https://raw.githubusercontent.com/diazoxide/autoteam/main/scripts/install.sh | bashInitialize a new project
Run autoteam init in your project directory to create the initial configuration. Optionally use a template to scaffold a common setup.
autoteam init --template development-teamEdit the YAML configuration
Open the generated autoteam.yaml and define your workers, MCP servers, and workflow flows. Each worker maps to an AI provider and prompt; flows define the orchestration logic.
workers:
- name: "Code Reviewer"
enabled: true
prompt: "Review pull requests for quality, security, and style issues"
settings:
mcp_servers:
github:
command: /opt/autoteam/bin/github-mcp-server
args: ["stdio"]
flow:
- name: review_prs
type: claude
prompt: "Check open PRs and post review comments using GitHub MCP tools"Deploy the agent team
Generate any additional config files and bring up the containerized agent team.
autoteam generate
autoteam upAccess the control plane API
The Autoteam control plane API is available at http://localhost:9090, with Swagger UI documentation at http://localhost:9090/docs/. Use this to monitor agents, trigger workflows, and inspect results.
Connect an MCP client to the Autoteam endpoint
Point your MCP client at the Autoteam MCP endpoint to interact with the orchestration layer through natural language.
{
"mcpServers": {
"autoteam": {
"command": "autoteam",
"args": ["mcp"],
"env": {}
}
}
}Autoteam Orchestration Examples
Client configuration
Claude Desktop configuration to connect to a running Autoteam instance via its MCP interface.
{
"mcpServers": {
"autoteam": {
"command": "autoteam",
"args": ["mcp"],
"env": {
"AUTOTEAM_API_URL": "http://localhost:9090"
}
}
}
}Prompts to try
These prompts show how to orchestrate multi-agent workflows through the Autoteam MCP interface.
- "List all active workers in the Autoteam deployment."
- "Trigger the review_prs workflow and report which pull requests were reviewed."
- "Add a new worker called 'Doc Writer' that generates documentation for merged PRs."
- "Show the status of all running workflows and highlight any that are stuck."
- "Create a YAML workflow that monitors the main branch and posts a Slack message when a PR is merged."Troubleshooting Autoteam Orchestration
autoteam up fails with a Docker permission error
Add your user to the docker group: sudo usermod -aG docker $USER, then log out and back in. On macOS, ensure Docker Desktop is running before executing autoteam up.
Agents start but fail to call MCP tool endpoints
Verify the MCP server binaries referenced in your YAML config exist at the specified paths. The GitHub and Slack MCP servers are bundled in /opt/autoteam/bin/ after installation — check they were installed with: ls /opt/autoteam/bin/
Control plane API returns 502 immediately after autoteam up
The containers may still be initializing. Wait 10-15 seconds and retry. Check container logs with: docker logs autoteam-control-plane to see if there are startup errors such as missing API keys.
Frequently Asked Questions about Autoteam Orchestration
What is Autoteam Orchestration?
Autoteam Orchestration is a Model Context Protocol (MCP) server that orchestrate ai agents with yaml-driven workflows via universal model context protocol (mcp) It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Autoteam Orchestration?
Follow the installation instructions on the Autoteam Orchestration GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Autoteam Orchestration?
Autoteam Orchestration works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Autoteam Orchestration free to use?
Yes, Autoteam Orchestration is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Autoteam Orchestration Alternatives — Similar Coding Agents Servers
Looking for alternatives to Autoteam Orchestration? 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 Autoteam Orchestration 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 Autoteam Orchestration?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.