MCP Crew AI Server

@adam-paterson

Repository

Basic information

About MCP Crew AI Server

MCP Crew AI Server is a lightweight Python-based server designed to run, manage and create CrewAI workflows.

#ai #mcp #agents #mcp-server

MCP Crew AI Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-crew-ai": {
      "command": "uvx",
      "args": [
        "mcp-crew-ai",
        "--agents",
        "path/to/agents.yml",
        "--tasks",
        "path/to/tasks.yml"
      ]
    }
  }
}

MCP Crew AI Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is MCP Crew AI Server?

MCP Crew AI Server is a lightweight Python server that runs, manages, and creates CrewAI multi-agent workflows. It uses the Model Context Protocol (MCP) to communicate with LLMs and tools like Claude Desktop or Cursor IDE, enabling orchestration of agentic tasks without custom code.

How to use MCP Crew AI Server?

Install via pip install mcp-crew-ai (or from GitHub or clone). Run with mcp-crew-ai --agents path/to/agents.yml --tasks path/to/tasks.yml or using uvx mcp-crew-ai with the same flags. Additional options include --topic, --process, --verbose, and --variables for YAML templating.

Key features of MCP Crew AI Server

Automatically loads agent/task configs from agents.yml and tasks.yml.
Supports custom YAML paths via --agents and --tasks command arguments.
Runs workflows through the MCP run_workflow tool.
Operates locally in STDIO mode for development and testing.
Allows variable substitution in YAML files via --variables.
Offers sequential or hierarchical process types.

Use cases of MCP Crew AI Server

Automating multi-step research and reporting tasks with AI agents.
Generating content (e.g., zoo updates) by assigning roles and goals.
Running templated workflows from IDEs like Cursor or from Claude Desktop.
Rapidly prototyping CrewAI workflows without writing Python code.

Frequently asked questions

What is the runtime requirement?

Python 3.11+ along with MCP SDK, CrewAI, and PyYAML.

Can I use custom configuration files?

Yes, you specify paths via `--agents` and `--tasks` command line options.

How does variable substitution work?

Use `--variables` with a JSON string or file path; placeholders like `{topic}` in YAML are replaced at runtime.

Does it support different workflow processes?

Yes, you can choose `sequential` (default) or `hierarchical` with the `--process` flag.

Is there a default configuration if no files are given?

No; both `--agents` and `--tasks` are required when running the server with `mcp-crew-ai`. The `uvx mcp-crew-ai-server` command uses defaults from environment variables.

Comments

More Reasoning MCP servers

iFlytek Workflow MCP Server

iflytek

This a simple implementation of an MCP server using iFlytek. It enables calling iFlytek workflows through MCP tools.

Agentic Resource Discovery

neuronto

Neuronto Agentic Resource Discovery (ARD) Index. Federated search across every public ARD registry, plus a verified tool index read from each MCP server's own tools/list, hybrid lexical and semantic retrieval, and ARD-Bench.

MCP Servers

junfanz1

This project demonstrates a decoupled real-time agent architecture that connects LangGraph agents to remote tools served by custom MCP (Modular Command Protocol) servers. The architecture enables a flexible and scalable multi-agent system where each tool can be hosted independent

n8n Workflow Builder MCP Server

makafeli

AI assistant integration for n8n workflow automation through Model Context Protocol (MCP). Connect Claude Desktop, ChatGPT, and other AI assistants to n8n for natural language workflow management.

530

🚀 Aider-MCP: AI Coding Server with Universal Auto-Detection

jacv888

Aider-MCP-Upgraded is a production-grade multi-agent AI coding system that combines Desktop Commander (DC) investigation capabilities with Aider's implementation power. Features 70%+ token reduction, modular architecture, and intelligent workflow automation through strategic agen