Anemoi
Anemoi: A Semi-Centralized Multi-agent Systems Based on Agent-to-Agent Communication MCP server from Coral Protocol
What is Anemoi?
Anemoi is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to anemoi: a semi-centralized multi-agent systems based on agent-to-agent communication mcp server from coral protocol
Anemoi: A Semi-Centralized Multi-agent Systems Based on Agent-to-Agent Communication MCP server from Coral Protocol
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Anemoi: A Semi-Centralized Multi-agent Systems Based on Agen
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx anemoiConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Anemoi
Anemoi is a semi-centralized multi-agent system built on Coral Protocol that enables direct agent-to-agent (A2A) communication through an MCP server interface. It coordinates multiple specialized AI agents — including web search, document processing, and coding agents — allowing them to monitor each other's progress, exchange results, and iteratively refine outputs. Teams building complex AI pipelines use Anemoi to orchestrate distributed agents that collaborate on research, data extraction, and multi-step problem solving.
Prerequisites
- Python 3.12 installed (the virtual environment must use exactly Python 3.12)
- API keys for the services your agents will use: OPENROUTER_API_KEY, GOOGLE_API_KEY, FIRECRAWL_API_KEY, CHUNKR_API_KEY, and SEARCH_ENGINE_ID
- An MCP-compatible client such as Claude Desktop
- Git for cloning the repository
Clone the Anemoi repository
Clone the Coral Protocol Anemoi repository to your local machine.
git clone https://github.com/Coral-Protocol/Anemoi.git && cd AnemoiCreate a Python 3.12 virtual environment
Create and activate a virtual environment using Python 3.12 specifically, as required by the CAMEL dependencies.
/usr/bin/python3.12 -m venv venv && source venv/bin/activateInstall Python dependencies
Install all required packages from the requirements file into your virtual environment.
pip install -r requirements.txtApply the patched CAMEL library
Anemoi uses a customized fork of CAMEL 0.2.70. Replace the installed version with the patched copy included in the repository.
rm -rf venv/lib/python3.12/site-packages/camel && cp -r utils/camel venv/lib/python3.12/site-packages/Set required environment variables
Export your API keys before starting the server. Add these to your shell profile or a .env file for convenience.
export OPENROUTER_API_KEY=your_key_here
export GOOGLE_API_KEY=your_key_here
export FIRECRAWL_API_KEY=your_key_here
export CHUNKR_API_KEY=your_key_here
export SEARCH_ENGINE_ID=your_engine_id
export HF_HOME=/path/to/hf_cacheConfigure Claude Desktop to use Anemoi
Add the Anemoi MCP server to your Claude Desktop configuration, pointing to the virtual environment's Python executable.
{
"mcpServers": {
"anemoi": {
"command": "/path/to/Anemoi/venv/bin/python",
"args": ["-m", "anemoi"],
"env": {
"OPENROUTER_API_KEY": "your_key_here",
"GOOGLE_API_KEY": "your_key_here",
"FIRECRAWL_API_KEY": "your_key_here",
"SEARCH_ENGINE_ID": "your_engine_id"
}
}
}
}Anemoi Examples
Client configuration
Claude Desktop configuration for the Anemoi multi-agent MCP server with required API keys.
{
"mcpServers": {
"anemoi": {
"command": "/path/to/Anemoi/venv/bin/python",
"args": ["-m", "anemoi"],
"env": {
"OPENROUTER_API_KEY": "your_openrouter_key",
"GOOGLE_API_KEY": "your_google_key",
"FIRECRAWL_API_KEY": "your_firecrawl_key",
"CHUNKR_API_KEY": "your_chunkr_key",
"SEARCH_ENGINE_ID": "your_search_engine_id"
}
}
}
}Prompts to try
Example prompts to orchestrate multi-agent workflows through Anemoi.
- "Research the latest advances in transformer architecture and compile a structured report"
- "Coordinate agents to scrape product data from these URLs and extract pricing into a spreadsheet"
- "Use multiple agents to analyze this document collection and identify common themes"
- "Orchestrate a research pipeline that searches, reads, and summarizes five papers on RAG systems"Troubleshooting Anemoi
CAMEL import errors after installation
Ensure you ran the cp command to replace the default CAMEL installation with the patched version in utils/camel. Reinstalling via pip will overwrite this; always re-apply the patch after running pip install.
Agents fail with API authentication errors
Verify all required environment variables (OPENROUTER_API_KEY, GOOGLE_API_KEY, FIRECRAWL_API_KEY, CHUNKR_API_KEY, SEARCH_ENGINE_ID) are set in the environment where the server runs, not just in your terminal session.
Python version mismatch errors during venv creation
The project requires exactly Python 3.12. Run 'python3.12 --version' to confirm availability. If missing, install Python 3.12 from python.org or via your system package manager before creating the venv.
Frequently Asked Questions about Anemoi
What is Anemoi?
Anemoi is a Model Context Protocol (MCP) server that anemoi: a semi-centralized multi-agent systems based on agent-to-agent communication mcp server from coral protocol It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Anemoi?
Follow the installation instructions on the Anemoi GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Anemoi?
Anemoi works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Anemoi free to use?
Yes, Anemoi is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Anemoi Alternatives — Similar Coding Agents Servers
Looking for alternatives to Anemoi? 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 Anemoi 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 Anemoi?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.