Bull Vision Agent
A FastAPI application that integrates with Telegram using webhooks and OpenAI Agents SDK for AI-powered stock trading assistance, utilizing MCPHub for multiple MCP server management.
What is Bull Vision Agent?
Bull Vision Agent is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to fastapi application that integrates with telegram using webhooks and openai agents sdk for ai-powered stock trading assistance, utilizing mcphub for multiple mcp server management.
A FastAPI application that integrates with Telegram using webhooks and OpenAI Agents SDK for AI-powered stock trading assistance, utilizing MCPHub for multiple MCP server management.
This server falls under the Finance & Fintech category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A FastAPI application that integrates with Telegram using we
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx bull-vision-agentConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Bull Vision Agent
Bull Vision Agent is an AI-powered stock trading assistant delivered through Telegram, built on FastAPI and the OpenAI Agents SDK with MCPHub for multi-server MCP management. It connects to Telegram via webhooks to receive user messages and responds with AI-generated stock analysis, news summaries, and volume wall detection powered by Azure OpenAI. Traders and developers use it to get real-time market intelligence through a familiar chat interface without building a dedicated frontend.
Prerequisites
- Python 3.10 or higher and Poetry installed
- A Telegram bot token from @BotFather
- Azure OpenAI credentials: API key, endpoint, deployment name, and API version
- A MongoDB instance (local or cloud, e.g. MongoDB Atlas)
- A publicly accessible server or tunnel (e.g. ngrok) for webhook delivery
Clone the repository and install dependencies
Clone the Bull Vision Agent repo and use Poetry to install all Python dependencies in an isolated virtual environment.
git clone https://github.com/Cognitive-Stack/bull-vision-agent.git
cd bull-vision-agent
poetry installCreate your Telegram bot
Open Telegram and message @BotFather with /newbot. Follow the prompts to choose a name and username. Copy the bot token provided — you will need it for the TELEGRAM_BOT_TOKEN environment variable.
Configure environment variables
Copy the example .env file and fill in all required values: your Telegram bot token, public webhook URL, Azure OpenAI credentials, and MongoDB connection details.
cp .env.example .env
# Edit .env with your values:
# TELEGRAM_BOT_TOKEN=your_bot_token
# TELEGRAM_WEBHOOK_URL=https://yourdomain.com/webhook
# HOST=0.0.0.0
# PORT=8000
# AZURE_OPENAI_API_KEY=your_key
# AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com
# AZURE_OPENAI_DEPLOYMENT=gpt-4o
# AZURE_OPENAI_API_VERSION=2024-02-01
# MONGO_URI=mongodb+srv://user:[email protected]
# MONGO_DB=bull_visionExpose your server publicly
For local development, use ngrok or a similar tunneling tool to expose your FastAPI server so Telegram can deliver webhook events. Set the resulting HTTPS URL as TELEGRAM_WEBHOOK_URL in your .env file.
ngrok http 8000Start the agent
Use the make target to launch the FastAPI server. It will register the Telegram webhook automatically on startup.
make runInteract with your bot on Telegram
Open Telegram, find your bot by its username, and send /start to begin. You can then ask it to analyze stocks, check news, or detect volume patterns.
Bull Vision Agent Examples
Client configuration
Bull Vision Agent runs as a standalone FastAPI service rather than a typical MCP client config. The .env file below shows the full configuration surface.
{
"TELEGRAM_BOT_TOKEN": "123456:ABC-DEF...",
"TELEGRAM_WEBHOOK_URL": "https://yourdomain.com/webhook",
"HOST": "0.0.0.0",
"PORT": "8000",
"AZURE_OPENAI_API_KEY": "your_azure_key",
"AZURE_OPENAI_ENDPOINT": "https://your-resource.openai.azure.com",
"AZURE_OPENAI_DEPLOYMENT": "gpt-4o",
"AZURE_OPENAI_API_VERSION": "2024-02-01",
"MONGO_URI": "mongodb+srv://user:[email protected]",
"MONGO_DB": "bull_vision"
}Prompts to try
Send these messages to your Telegram bot after it is running.
- "Analyze AAPL and give me a summary of today's performance"
- "What's the latest news about Tesla stock?"
- "Check volume patterns for MSFT and flag any unusual walls"
- "Show me a market overview for the tech sector today"Troubleshooting Bull Vision Agent
Telegram webhook registration fails or bot does not respond
Ensure your TELEGRAM_WEBHOOK_URL is a valid HTTPS URL reachable from the internet. When using ngrok, restart ngrok each session since the URL changes — update .env and restart the server to re-register.
Azure OpenAI calls return 401 or deployment not found
Double-check AZURE_OPENAI_DEPLOYMENT matches the exact deployment name (not the model name) in your Azure OpenAI Studio. Also verify the API version string matches a supported version for your resource region.
MongoDB connection error on startup
Confirm your MONGO_URI is a valid connection string and that your IP address is whitelisted in MongoDB Atlas Network Access settings. For local MongoDB, ensure the service is running on the expected port.
Frequently Asked Questions about Bull Vision Agent
What is Bull Vision Agent?
Bull Vision Agent is a Model Context Protocol (MCP) server that fastapi application that integrates with telegram using webhooks and openai agents sdk for ai-powered stock trading assistance, utilizing mcphub for multiple mcp server management. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Bull Vision Agent?
Follow the installation instructions on the Bull Vision Agent GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Bull Vision Agent?
Bull Vision Agent works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Bull Vision Agent free to use?
Yes, Bull Vision Agent is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Bull Vision Agent Alternatives — Similar Finance & Fintech Servers
Looking for alternatives to Bull Vision Agent? Here are other popular finance & fintech servers you can use with Claude, Cursor, and VS Code.
ValueCell
★ 10.7kValueCell is a community-driven, multi-agent platform for financial applications.
Vibe Trading
★ 8.1k'Vibe-Trading: Your Personal Trading Agent'
Quantdinger
★ 6.2kAI quantitative trading platform for crypto, stocks, and forex with backtesting, live trading, market data, and multi-agent research.vibe-trading ,trading-agents,ai-trader,ai-trading
TradingView
★ 2.8kReal-time crypto & stock screening, advanced technical indicators, Bollinger Bands intelligence, candlestick patterns + native Claude Desktop integration. Multi-exchange (Binance, KuCoin, Bybit+). Open-source AI trading infrastructure.
Financial Datasets
★ 2.1kProvides access to comprehensive financial data including income statements, balance sheets, cash flow statements, stock prices, company news, SEC filings, and cryptocurrency information with built-in financial ratio analysis.
Stripe
★ 1.6kThe Stripe Model Context Protocol server allows you to integrate with Stripe APIs through function calling. This protocol supports various tools to interact with different Stripe services.
Browse More Finance & Fintech MCP Servers
Explore all finance & fintech servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Bull Vision Agent 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 Bull Vision Agent?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.