MCP Crew AI Server
by adam-paterson
MCP Crew AI Server is a lightweight Python-based server designed to run, manage and create CrewAI workflows. It leverages the Model Context Protocol (MCP) to communicate with Large Language Models (LLMs) and tools, allowing you to orchestrate multi-agent workflows with ease.
Last updated: N/A
What is MCP Crew AI Server?
MCP Crew AI Server is a Python-based server that facilitates the creation, management, and execution of CrewAI workflows. It uses the Model Context Protocol (MCP) for communication with LLMs and tools.
How to use MCP Crew AI Server?
Install the server using pip or by cloning the GitHub repository. Configure agents and tasks using YAML files (agents.yml and tasks.yml). Run the server using the mcp-crew-ai command, providing paths to your configuration files. You can also use uvx for a more streamlined experience.
Key features of MCP Crew AI Server
Automatic Configuration from YAML files
Command Line Flexibility for configuration paths
Seamless Workflow Execution through MCP
Local Development support in STDIO mode
Use cases of MCP Crew AI Server
Automated report generation using multiple AI agents.
Orchestrating complex tasks involving different LLMs.
Building AI-powered virtual assistants with coordinated roles.
Creating custom AI workflows for specific business needs.
FAQ from MCP Crew AI Server
What is the Model Context Protocol (MCP)?
What is the Model Context Protocol (MCP)?
MCP is a protocol for communicating with Large Language Models (LLMs) and tools.
How do I configure agents and tasks?
How do I configure agents and tasks?
Agents and tasks are configured using YAML files (agents.yml and tasks.yml).
Can I use custom configuration file paths?
Can I use custom configuration file paths?
Yes, you can specify custom paths using the --agents and --tasks command-line arguments.
What are the system requirements?
What are the system requirements?
Python 3.11+, MCP SDK, CrewAI, and PyYAML are required.
How can I contribute to the project?
How can I contribute to the project?
Contributions are welcome! Please open issues or submit pull requests with improvements, bug fixes, or new features.