Crewai MCP Demo
Repository for CrewAI MCP demo codebase
Ask AI about Crewai MCP Demo
Powered by Claude ยท Grounded in docs
I know everything about Crewai MCP Demo. Ask me about installation, configuration, usage, or troubleshooting.
0/500
Reviews
Documentation
CrewAI MCP Demo
This repository demonstrates different approaches for using CrewAI with MCP (Model Context Protocol) to interact with external tools and services through a standardized protocol.
๐ Featured Examples
๐ญ Enterprise Regulatory Intelligence
๐ Location: scaffolding_approach_examples/snowflake_mcp_demo/
A production-ready 3-agent system that combines CrewAI's multi-agent orchestration with Snowflake's enterprise data capabilities to build regulatory intelligence systems.
Key Features:
- ๐ค 3-Agent Coordination: Regulatory Intelligence + SEC Filing Analysis + Market News
- ๐ Enterprise Scale: Semantic search across 372,299 SEC filings via Snowflake MCP
- ๐ฏ Professional Output: Investment-grade regulatory impact reports
- ๐ Production Ready: Complete deployment and configuration examples
๐ Two Integration Approaches
This repository demonstrates two different ways to integrate CrewAI with MCP:
1. ๐๏ธ Scaffolding Approach (Recommended for Production)
- Uses CrewAI's project scaffolding with
@CrewBasedecorator - Structured project with configuration files
- Built-in
get_mcp_tools()method (CrewAI 0.134.0+) - Better for complex, maintainable applications
Examples:
- Snowflake Enterprise Demo - Regulatory intelligence system
- Mathematician Project - Math operations via local StdIO server
- Context7 Integration - Document search via streamable-HTTP
2. ๐ Script Approach (Great for Learning/Prototyping)
- Standalone Python scripts using
MCPServerAdapterdirectly - Quick to set up and experiment with
- Perfect for understanding MCP concepts
Examples:
stdio_client_demo.py- Math operationssse_client_demo.py- Cloudflare docs searchstreamable_http_client_demo.py- Simple greetingmultiple_servers_client_demo.py- Combined functionality
๐ง Transport Mechanisms
Streamable HTTP โญ (Recommended)
- Use case: Remote hosted servers (Context7, cloud services)
- Benefits: Simple setup, bidirectional communication, web-friendly
- Example: Snowflake MCP, Context7 API
Server-Sent Events (SSE)
- Use case: Real-time server-to-client updates
- Benefits: Good for streaming responses, widely supported
- Example: Cloudflare docs, real-time data feeds
Standard Input/Output (StdIO)
- Use case: Local development, testing, process-based servers
- Benefits: Simple local setup, no network required
- Example: Local math server, file processing tools
๐ Project Structure
crewai-mcp-demo/
โโโ ๐๏ธ scaffolding_approach_examples/
โ โโโ snowflake_mcp_demo/ # ๐ FEATURED: Enterprise regulatory intelligence
โ โโโ mathematician_project/ # Math operations via local StdIO server
โ โโโ crewai_context7_mcp/ # Context7 integration via streamable-HTTP
โโโ ๐ script_approach_examples/ # Standalone script examples
โ โโโ stdio_client_demo.py # Math operations via StdIO
โ โโโ sse_client_demo.py # Cloudflare docs via SSE
โ โโโ streamable_http_client_demo.py # Greeting via HTTP
โ โโโ multiple_servers_client_demo.py # Multiple servers example
โโโ ๐ฅ๏ธ servers/ # Local MCP servers
โ โโโ hello_http_server.py # HTTP greeting server
โ โโโ math_stdio_server.py # StdIO math server
โโโ README.md # This file
โก Quick Start
Option 1: Try the Enterprise Demo (Recommended)
cd scaffolding_approach_examples/snowflake_mcp_demo/
# Follow the detailed setup guide in that directory
Option 2: Try a Simple Script
# For math operations (local server)
python3 script_approach_examples/stdio_client_demo.py
# For Cloudflare docs (remote server)
python3 script_approach_examples/sse_client_demo.py
๐ ๏ธ Prerequisites
- Python: Version >= 3.10 < 3.14
- CrewAI: Version >= 0.134.0 (for scaffolding approach)
- API Keys: Depends on the example (OpenAI, Snowflake, etc.)
- uv (recommended) or pip for package management
๐ Learn More
Featured Documentation
- ๐ญ Enterprise Regulatory Intelligence Tutorial - Complete production system
- ๐งฎ Mathematician Project - Local MCP server integration
- ๐ Context7 Integration - Cloud MCP service
Resources
๐ค Contributing
Contributions welcome! Areas where we'd love help:
- Additional MCP server examples
- More transport mechanism demos
- Documentation improvements
- Bug fixes and optimizations
๐ License
This project is licensed under the MIT License - see the LICENSE.md file for details.
โญ Star History
Happy building with CrewAI and MCP! ๐
