AI Prediction MCP Server

MCPServer_aiprediction_us

AI Prediction MCP Server

Repository Views GitHub Stars GitHub Forks GitHub Issues License

A Model Context Protocol (MCP) server that provides Claude with access to AI prediction data from the aiprediction.us API.

AI Prediction MCP Server

A Model Context Protocol (MCP) server that provides Claude with access to AI prediction data from the aiprediction.us API. This server handles authentication, date formatting, and data retrieval to give Claude seamless access to trading predictions and analysis.

🚀 Features

Automatic Authentication: Handles token-based authentication with the AI Prediction API
Date Management: Converts dates to YYMMDD format and gets current date automatically
Real-time Data: Retrieves last elements data for any date
Error Handling: Comprehensive logging and error recovery
Token Management: Automatic token refresh when expired

📋 Prerequisites

Python 3.8 or higher
Active account on aiprediction.us
Claude Desktop (or another MCP-compatible client)

🛠️ Installation

1. Clone or Download Files

Download these files to your project directory:

MCPServer.py (the main MCP server)
requirements.txt (Python dependencies)
.env.example (environment configuration template)

2. Set Up Python Environment

Option A: Using venv (Recommended)

# Create virtual environment
python -m venv aiprediction-mcp
cd aiprediction-mcp

# Activate virtual environment
# On Windows:
Scripts\activate
# On macOS/Linux:
source bin/activate

# Install dependencies
pip install -r requirements.txt

Option B: Using conda

# Create conda environment
conda create -n aiprediction-mcp python=3.9
conda activate aiprediction-mcp

# Install dependencies
pip install -r requirements.txt

Option C: Global Installation

# Install directly (not recommended for production)
pip install mcp aiohttp python-dotenv

3. Configure Environment Variables

Copy the example file:
cp .env.example .env
Edit .env with your credentials:
# AI Prediction API Configuration API_BASE_URL=https://aiprediction.us API_USERNAME=your_username_here API_PASSWORD=your_password_here
Replace your_username_here and your_password_here with your actual aiprediction.us credentials.

🎯 Running the MCP Server

Test the Server

python aiprediction-mcp-server.py

You should see output like:

📁 .env file loaded successfully
🚀 Starting AI Prediction MCP Server
🌐 API Base URL: https://aiprediction.us
🔐 Attempting authentication...
✅ Authentication successful!
✅ Token received: 190a0687f8db55f3640c...
📊 Testing data retrieval...
✅ Successfully retrieved data for 250613
🎯 MCP Server ready for connections

If you see errors:

Missing credentials: Check your .env file
Authentication failed: Verify your username/password
API errors: Check your network connection

Keep Server Running

The MCP server needs to stay running while you use Claude. You can:

Run it in a terminal and keep it open
Use screen/tmux for persistent sessions
Run as a background service

🔧 Configure Claude Desktop

1. Find Claude's Configuration File

macOS:

~/Library/Application Support/Claude/claude_desktop_config.json

Windows:

%APPDATA%/Claude/claude_desktop_config.json

2. Add MCP Server Configuration

Edit the configuration file and add your MCP server:

{
  "mcpServers": {
    "aiprediction": {
      "command": "python",
      "args": ["/full/path/to/your/MCPerver.py"],
      "env": {
        "API_BASE_URL": "https://aiprediction.us",
        "API_USERNAME": "your_username",
        "API_PASSWORD": "your_password"
      }
    }
  }
}

Important: Replace /full/path/to/your/aiprediction-mcp-server.py with the actual full path to your script.

3. Restart Claude Desktop

Close and reopen Claude Desktop to load the new configuration.

💬 Using Claude with AI Prediction Data

Once configured, you can ask Claude to access your AI prediction data:

Example Queries

Get Today's Data:

Get today's AI prediction data

Get Specific Date:

Get the prediction data for December 15, 2024

What's the data for 250612?

Date Conversion:

Convert March 15, 2025 to YYMMDD format

Historical Analysis:

Compare prediction data between 241201 and 241215

Available Tools

Claude will have access to these tools:

get_current_date_data - Gets prediction data for today
get_last_elements_by_date - Gets data for any specific date
format_date_yymmdd - Converts dates to YYMMDD format
get_api_debug_info - Gets API status and debug information

Data Structure

The API returns data with this structure:

{
  "DID": "250613",
  "ID": 421,
  "ctime": ["09:30 AM", "09:31 AM", ...],
  "lookup_method": "did",
  "last_elements": {
    "sp": 5970.62,
    "es": 5972.75,
    "p1": 5970.0,
    "c1": 5975.0,
    // ... more prediction fields
  }
}

🔍 Troubleshooting

Common Issues

1. "Missing credentials" Error

Check your .env file exists and has correct format
Ensure no extra spaces around the = signs
Verify file is in same directory as the script

2. "Authentication failed" Error

Verify your username and password are correct
Check if your aiprediction.us account is active
Try logging in via the website first

3. "MCP Server not found" in Claude

Check the full path in claude_desktop_config.json
Ensure Python is in your system PATH
Try using absolute path to Python executable

4. "No data found" for specific dates

Some dates may not have prediction data
Try recent trading days (weekdays)
Check if the date format is correct (YYMMDD)

Debug Mode

To see detailed logging, you can modify the server to show more information:

# Run with Python's verbose output
python -v aiprediction-mcp-server.py

Check Configuration

Verify Claude can see your MCP server:

Open Claude Desktop
Look for MCP server indicators in the interface
Try asking: "What MCP tools do you have access to?"

📚 API Reference

Environment Variables

Variable	Required	Description
`API_BASE_URL`	Yes	Base URL for the API (https://aiprediction.us)
`API_USERNAME`	Yes	Your aiprediction.us username
`API_PASSWORD`	Yes	Your aiprediction.us password

Date Format

The API uses YYMMDD format:

250613 = June 13, 2025
241225 = December 25, 2024
240101 = January 1, 2024

Available Endpoints

The MCP server accesses these API endpoints:

POST /api-token-auth/ - Authentication
GET /api/v53a/{did}/last-elements/ - Get prediction data
GET /api/debug/v53a/general/ - Debug information

🤝 Contributing

To improve this MCP server:

Fork the repository
Make your changes
Test with your AI Prediction account
Submit a pull request

📄 License

This project is licensed under the MIT License.

🆘 Support

For issues:

Check the troubleshooting section above
Verify your aiprediction.us account works via their website
Test the MCP server output for detailed error messages
Check Claude Desktop's MCP configuration

Happy Trading with AI Predictions! 📈# aiprediction_us_MCP_Server

This server cannot be installed

security - not tested

license - not found

quality - not tested

hybrid server

The server is able to function both locally and remotely, depending on the configuration or use case.

A Model Context Protocol server that provides Claude with access to AI-powered trading predictions and analysis from the aiprediction.us API, handling authentication, date formatting, and data retrieval.

Related MCP Servers

MTS MCP Server
CalvinMagezi
-
security
F
license
-
quality
A comprehensive suite of Model Context Protocol servers designed to extend AI agent Claude's capabilities with integrations for knowledge management, reasoning, advanced search, news access, and workspace tools.
Last updated -
5
TypeScript
API Tester MCP Server
Vikrant-Khedkar
-
security
F
license
-
quality
A Model Context Protocol server that allows Claude to make API requests on your behalf, providing tools for testing various APIs including HTTP requests and OpenAI integrations without sharing your API keys in the chat.
Last updated -
Python
Prem MCP Server
ucalyptus
-
security
F
license
-
quality
A Model Context Protocol server implementation that enables seamless integration with Claude and other MCP-compatible clients to access Prem AI's language models, RAG capabilities, and document management features.
Last updated -
JavaScript
Financial Modeling Prep MCP Server
shadi-fsai
-
security
A
license
-
quality
A Model Context Protocol server that enables AI assistants like Claude to programmatically access financial data from Financial Modeling Prep API, including company profiles, financial statements, metrics, SEC filings, and market data.
Last updated -
5
Python
MIT License

View all related MCP servers

MCPServer_aiprediction_us

AI Prediction MCP Server

AI Prediction MCP Server

🚀 Features

📋 Prerequisites

🛠️ Installation

1. Clone or Download Files

2. Set Up Python Environment

Option A: Using venv (Recommended)

Option B: Using conda

Option C: Global Installation

3. Configure Environment Variables

🎯 Running the MCP Server

Test the Server

Keep Server Running

🔧 Configure Claude Desktop

1. Find Claude's Configuration File

2. Add MCP Server Configuration

3. Restart Claude Desktop

💬 Using Claude with AI Prediction Data

Example Queries

Available Tools

Data Structure

🔍 Troubleshooting

Common Issues

Debug Mode

Check Configuration

📚 API Reference

Environment Variables

Date Format

Available Endpoints

🤝 Contributing

📄 License

🆘 Support

Related MCP Servers

MTS MCP Server

API Tester MCP Server

Prem MCP Server

Financial Modeling Prep MCP Server

New MCP Servers

MCP directory API