FRED MCP Server
A Model Context Protocol server that provides access to Federal Reserve Economic Data (FRED), enabling users to retrieve, analyze, and compare economic indicators and time series data through natural language.
README
FRED MCP Server
https://github.com/user-attachments/assets/059030bf-141b-4399-99aa-a2cd51abdf05
A Model Context Protocol (MCP) server for accessing and analyzing Federal Reserve Economic Data (FRED).
Overview
This server provides access to Federal Reserve Economic Data (FRED) using the FRED API through the Model Context Protocol.
Features
- Economic Data Access: Retrieve economic indicators and time series data from FRED
- Trend Analysis: Analyze economic trends over time
- Comparative Analysis: Compare multiple economic indicators
- Metadata Access: Get information about available economic series
- Prompt Templates: Use pre-defined prompt templates for common economic analysis tasks
Installation
Prerequisites
- Python 3.10 or higher
- A FRED API key (for the backend service)
Install from Source
# Clone the repository
git clone https://github.com/yourusername/fred-mcp-server.git
cd fred-mcp-server
# Create a virtual environment
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
# Install the package
# Install with pip
pip install .
# Install with UV (recommended for exact dependency versions)
uv pip install .
Configuration
The server can be configured using environment variables:
FRED_API_KEY: Your FRED API key (required)LOG_LEVEL: Logging level (default: "INFO")LOG_FILE: Log file path (default: "fred_mcp_server.log")
Usage
Running the Server
# Run directly
python -m fred_mcp_server
# Or using the installed script
fred-mcp
Using with Claude for Desktop
To use with Claude for Desktop, add this server to your Claude configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"fred": {
"command": "uv",
"args": [
"run",
"-m",
"fred_mcp_server"
],
"cwd": "<PATH_TO_FRED_MCP_SERVER>/src",
"env": {
"FRED_API_KEY": "your_fred_api_key_here"
}
}
}
}
Notes:
- Replace
<PATH_TO_FRED_MCP_SERVER>with the absolute path to your fred directory - You can use
"command": "uv"with"args": ["run", "-m", "fred_mcp_server"]if using the uv package manager
Note: Replace your_fred_api_key_here with your actual FRED API key. You can obtain a free API key by registering at https://fred.stlouisfed.org/docs/api/api_key.html
Available Tools
All tools use a consistent fred_ prefix for clear namespace management:
search_fred_series: Search for economic data series by keywords or categoryfred_get_series_data: Retrieve time series data for a specific economic indicatorfred_get_series_metadata: Get detailed metadata about a specific economic data seriesfred_get_category_series: List series in a specific FRED categoryfred_get_releases: Get economic data releases from FREDfred_compare_series: Compare multiple economic indicators over a specified time periodfred_calculate_statistics: Calculate basic statistics for a FRED seriesfred_detect_trends: Identify trends in FRED economic dataanalyze_economic_trends: Analyze trends in economic indicators over time
Available Prompts
economic-data-search: How to effectively search for economic indicatorsdata-visualization-guide: How to create and interpret economic data visualizationstrend-analysis-guide: How to analyze trends in economic indicatorscomparative-analysis: How to perform comparative analysis of economic indicatorslatest-data-analysis: How to analyze the latest economic indicators
FRED API Disclaimer
This product uses the FRED® API but is not endorsed or certified by the Federal Reserve Bank of St. Louis. By using this product, you agree to comply with the FRED® API Terms of Use.
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。