Fedspeak MCP Server
Access and analyze Federal Reserve (FOMC) statements.
Fedspeak MCP Server
A Model Context Protocol (MCP) server for accessing and analyzing Federal Reserve (FOMC) statements.
Overview
This server provides a Model Context Protocol (MCP) interface for accessing and analyzing Federal Reserve (FOMC) statements. It enables semantic search and analysis of FOMC statements while handling all the complexity of data retrieval and processing behind a clean, tool-based interface.
Features
- Search Statements: Semantically search FOMC statements by topic, date, or content
- Metadata Access: Get information about available statements
- Trend Analysis: Analyze language trends in Fed statements over time
- Resource Access: Access full statement content as resources
- Prompt Templates: Use pre-defined prompt templates for common analysis tasks
Installation
Prerequisites
- Python 3.10 or higher
- A running private API server with access to the FOMC database
Install from Source
# Clone the repository
git clone https://github.com/yourusername/fomc-mcp-server.git
cd fomc-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:
FEDSPEAK_API_ENDPOINT: URL of the backend API service for data operations (default: "https://fedspeak-mcp-backend-671377599496.us-central1.run.app")LOG_LEVEL: Logging level (default: "INFO")LOG_FILE: Log file path (default: "fedspeak_mcp_server.log")
Note: No additional configuration is needed for data access - all required connections are handled automatically.
Usage
Running the Server
# Run directly
python -m fedspeak
# Or using the installed script
fedspeak
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": {
"fedspeak": {
"command": "uv",
"args": [
"--directory",
"/Users/mk/Documents/Python/AI Playground/mcp/fedspeak/src/fedspeak",
"run",
"fedspeak"
],
"env": {
"FEDSPEAK_API_ENDPOINT": "https://fedspeak-mcp-backend-671377599496.us-central1.run.app"
}
}
}
}
Note: This configuration uses UV to run the fedspeak server in a src-based package structure. The API endpoint connects to the Cloud Run backend service that handles all database operations and FOMC statement retrieval.
Available Tools
search_fomc_statements: Search Federal Reserve statements semanticallyget_fomc_metadata: Get metadata about available FOMC statementsanalyze_fomc_trends: Analyze trends in Federal Reserve language over timeget_latest_statement: Get the most recent FOMC statement with full text
Available Prompts
search-guidance: How to effectively search FOMC statementsanalyze-trends-guidance: How to analyze trends in FOMC language over timelatest-statement-analysis: How to analyze the latest FOMC statement
License
MIT
Server Terkait
CData Zoho Creator
A read-only MCP server by CData for querying live Zoho Creator data using a JDBC driver.
ODBC Server via PyODBC
An MCP server for connecting to databases like Virtuoso using ODBC drivers via pyodbc.
AWS RDS Management
Manage Amazon RDS and Aurora database clusters, including instances, backups, parameters, costs, and monitoring.
Local Context Memory MCP
A production-ready persistent memory system for AI agents, offering searchable memory across sessions with semantic search and support for multiple database backends.
Polygon MCP Server
Provides on-chain tools to interact with the Polygon PoS blockchain.
MCP ArcKnowledge
Manage and query custom knowledge bases using webhook endpoints.
Pinterest by CData
A read-only MCP server for querying live Pinterest data, powered by the CData JDBC Driver.
DICOM MCP Server
Enables AI assistants to query, read, and move data on DICOM servers such as PACS and VNA for medical imaging.
Supavec MCP Server
Fetch relevant content from Supavec, a vector database service.
CentralMind Gateway
Expose structured databases to AI agents via MCP or OpenAPI 3.1 protocols, with APIs optimized for AI workloads.