Fmp MCP Server

🚀 Financial Modeling Prep (FMP) MCP Server

This is a Model Context Protocol (MCP) server that provides access to data from the Financial Modeling Prep (FMP) API. It offers programmatic access to financial data for AI assistants (such as Claude) through a standardized interface.

✨ Features

• Company Overview: Obtain company information, descriptions, market capitalization, number of employees, and industry data.
• Financial Statements: Retrieve income statements, balance sheets, and cash - flow statements.
• Financial Metrics: Get key metrics, ratios, and growth data.
• Analyst Data: Access analyst estimates and recommendations.
• SEC Filings: Find and obtain the content of SEC filings.
• Earnings Transcripts: Get earnings call records.
• Market Data: Access current stock prices and Treasury yields.
• Competitor Analysis: Find competing companies.

📦 Installation

Prerequisites

• Python 3.8 or higher
• UV package manager (recommended) or pip
• Financial Modeling Prep API key

Setup

1. Clone this repository.
2. Create a .env file in the project root directory containing your API key:

   # Financial Modeling Prep API configuration
   FMP_KEY=your_api_key_here
   
   # Optional: SEC API configuration
   SEC_ACCESS=YourCompanyName YourEmail@example.com
   

3. Install dependencies using UV (recommended):

   uv venv
   uv pip install -r requirements.txt
   

   Or use pip:

   pip install -r requirements.txt
   

💻 Usage Examples

Running the Server

Using UV (Recommended)

UV provides faster dependency resolution and installation. To run the server using UV:

# Activate the virtual environment
uv venv activate

# Run the server
python fmp_mcp_server.py

The server will start and listen for connections on the default MCP port.

Using pip

# Create and activate a virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Run the server
python fmp_mcp_server.py

Connecting with Claude Desktop

Claude Desktop can connect to the MCP server to access financial data. Here's how to set it up:

1. Download Claude Desktop.
2. Edit claude_desktop_config.json:

"fmp_mcp_server": {
    "command": "uv",
    "args": [
        "--directory",
        "REPLACE ME WITH ABSOLUTE DIRECTORY TO REPO",
        "run",
        "fmp_mcp_server.py"
    ]
}

Now, Claude can use FMP data through the MCP interface. You can ask Claude to perform the following actions:

• Get company overviews.
• Retrieve financial statements.
• Find the latest 10 - K filing for Microsoft.
• Get the main competitors of Amazon.
• Get the latest earnings transcript of Meta.

🔧 Technical Details

Configuration Options

The server supports the following environment variables:

• FMP_KEY: Your Financial Modeling Prep API key (required).
• SEC_ACCESS: Your company name and email address for accessing the SEC API (optional).

Caching

The server implements a caching system to reduce API calls and improve performance:

• Financial data is cached quarterly/yearly.
• Profile data is cached monthly.
• Daily price data is cached on the day. The cache files are stored in the DataCache directory.

Logging

Logs are written to the logs directory with rotation enabled:

• Maximum log file size: 10MB.
• Number of backup files: 5.