# π€ MCP + CrewAI Agentic Integration π
A powerful demonstration of **Model Context Protocol (MCP)** integrated with **CrewAI** orchestrations, featuring full observability through **AgentOps** and high-speed inference via **Groq**.
---
## π Overview
This project bridges the gap between **context-aware tools** and **autonomous agents**. It provides a custom MCP server for real-time external data (Weather, News, Notes) while leveraging CrewAI to orchestrate multi-agent workflows.
### ποΈ Architecture
- **MCP Layer**: A `FastMCP` server exposing tools for real-time data retrieval.
* **Agentic Layer**: `CrewAI` agents specialized in Market Analysis and Research.
- **Inference Layer**: Ultra-fast LLMs (Llama 3.1) hosted on `Groq`.
- **Observability Layer**: `AgentOps` for tracing, cost management, and debugging.
---
## β¨ Key Features
### π οΈ Custom MCP Server Tools
- **βοΈ Weather Engine**: Real-time meteorology data via WeatherAPI.
- **π° News Intelligence**: Global news retrieval via Serper (Google Search API).
- **π Contextual Notes**: Locally persistent note management for long-term memory.
- **οΏ½ Auto-Summary**: Intelligent summarization of collected context.
### π₯ Intelligence Crew
- **π Market Researcher**: Scours data to identify emerging trends.
- **π Data Analyst**: Synthesizes research into actionable market insights.
- **π Sequential Workflow**: Fully orchestrated execution path for reliable results.
---
## π οΈ Tech Stack
- **Framework**: [CrewAI](https://crewai.com)
- **Server**: [FastMCP](https://modelcontextprotocol.io)
- **LLM Engine**: [Groq](https://groq.com) (Llama 3.1 8B/70B)
- **Tracing**: [AgentOps](https://agentops.ai)
- **Package Manager**: [uv](https://github.com/astral-sh/uv)
---
## π Getting Started
### 1. Prerequisites
Ensure you have the following installed:
- [uv](https://github.com/astral-sh/uv) (Recommended) or Python 3.13+
- A valid Groq API Key
- A valid AgentOps API Key
- A Serper API Key (for News)
### 2. Installation
Clone the repository and sync dependencies:
```bash
git clone https://github.com/vad-007/MCP_Integration_crewai.git
cd MCP_Integration_crewai
uv sync
```
### 3. Configuration
Create a `.env` file in the root directory:
```env
AGENTOPS_API_KEY=your_agentops_key
GROQ_API_KEY=your_groq_key
SERPER_API_KEY=your_serper_key
WEATHER_API_KEY=your_weather_key
```
### 4. Running the Project
#### π Start the MCP Server
```bash
mcp dev main.py
```
#### π’ Run the CrewAI Integration
```bash
python crewai_agentops_integration.py
```
#### π Run Diagnostics
```bash
python test_agentops.py
```
---
## π Observability with AgentOps
This project is fully instrumented. Every run generates a unique replay URL allowed you to:
- **Watch Agent Self-Correction**: See exactly how agents reason through tasks.
- **Trace LLM Calls**: Monitor every prompt and completion.
- **Analyze Latency**: Visualize the execution timeline of your crew.
Check your dashboard at: [app.agentops.ai](https://app.agentops.ai)
---
## π Project Structure
```text
βββ main.py # FastMCP Server implementation
βββ crewai_agentops_integration.py # Main CrewAI orchestration
βββ test_agentops.py # Connectivity & Diagnostic tool
βββ .env # Environment variables (private)
βββ pyproject.toml # Project configuration
βββ uv.lock # Dependency lockfile
βββ docs/ # Troubleshooting & Optimization guides
```
---
## π€ Contributing
Contributions are what make the open-source community such an amazing place to learn, inspire, and create. Any contributions you make are **greatly appreciated**.
1. Fork the Project
2. Create your Feature Branch (`git checkout -b feature/AmazingFeature`)
3. Commit your Changes (`git commit -m 'Add some AmazingFeature'`)
4. Push to the Branch (`git push origin feature/AmazingFeature`)
5. Open a Pull Request
---
## π‘οΈ License
Distributed under the MIT License. See `LICENSE` for more information.
---
**Developed with β€οΈ for the AI Community.**
