fred-mcp
Enables users to search, retrieve, and explore economic data series from the Federal Reserve Economic Data (FRED) API using natural language.
README
FRED MCP Server
An MCP server for the Federal Reserve Economic Data (FRED) API.
Features
- Search for economic data series.
- Retrieve data points for series.
- Explore Categories, Releases, Sources, and Tags.
- Pagination support for large datasets.
- Option to save data as JSON files.
Configuration
Set the FRED_API_KEY environment variable to your FRED API key.
Usage
Run with uvx (if published):
uvx fred-data-mcp
Installation from PyPI
Once published, you can install and run directly:
pip install fred-data-mcp
# or
uvx fred-data-mcp
Claude Desktop Configuration
To use this server with the Claude Desktop app, add the following to your claude_desktop_config.json:
Published Package (Recommended)
If you have published the package to PyPI, you can key off the package name directly:
{
"mcpServers": {
"fred": {
"command": "uvx",
"args": [
"fred-data-mcp"
],
"env": {
"FRED_API_KEY": "your_api_key_here"
}
}
}
}
Local Development
If you are running from the source code repository:
{
"mcpServers": {
"fred": {
"command": "uvx",
"args": [
"--from",
"/absolute/path/to/fred-mcp",
"fred-data-mcp"
],
"env": {
"FRED_API_KEY": "your_api_key_here"
}
}
}
}
Development
Running the MCP Inspector
To test the server locally with the MCP Inspector:
Windows (PowerShell):
$env:FRED_API_KEY = "your_api_key_here"
.\run-inspector.ps1
Bash:
export FRED_API_KEY="your_api_key_here"
./run-inspector.sh
Alternatively, run the command directly:
npx @modelcontextprotocol/inspector uv run fred-data-mcp
## Publication
### Publishing to PyPI
A helper script `publish.ps1` is provided to automate version bumping and publication.
**Requirements:**
- `uv` installed.
- PyPI credentials configured (e.g., via `~/.pypirc` or environment variables `TWINE_USERNAME` and `TWINE_PASSWORD`).
**Usage (Windows PowerShell):**
```powershell
# Bump patch version and publish
.\publish.ps1 patch
Usage (Bash):
# Bump patch version and publish
./publish.sh patch
To test the build process without uploading, use the -DryRun (PS) or --dry-run (Bash) flag:
.\publish.ps1 patch -DryRun
# or
./publish.sh patch --dry-run
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.