Skip to main content

MCP server for Federal Reserve Economic Data (FRED)

Project description

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

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

fred_data_mcp-0.1.5.tar.gz (112.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

fred_data_mcp-0.1.5-py3-none-any.whl (6.5 kB view details)

Uploaded Python 3

File details

Details for the file fred_data_mcp-0.1.5.tar.gz.

File metadata

  • Download URL: fred_data_mcp-0.1.5.tar.gz
  • Upload date:
  • Size: 112.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.4

File hashes

Hashes for fred_data_mcp-0.1.5.tar.gz
Algorithm Hash digest
SHA256 ac1c41877d44942439bd231094a42e394af16a30957815e6c90d634ef976ab90
MD5 dc19b2cf92e3660cf862ef85675ec9a6
BLAKE2b-256 3e32c7c84e13012bf422dc230be75883200482619cab11220faad1f22d741a1b

See more details on using hashes here.

File details

Details for the file fred_data_mcp-0.1.5-py3-none-any.whl.

File metadata

  • Download URL: fred_data_mcp-0.1.5-py3-none-any.whl
  • Upload date:
  • Size: 6.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.4

File hashes

Hashes for fred_data_mcp-0.1.5-py3-none-any.whl
Algorithm Hash digest
SHA256 7975d4ece3638ad760782d2aee39e361b61392525c2b0aa3ee13891917bb9848
MD5 df1f918f61bb0f81728a77476f594fb6
BLAKE2b-256 bbdea5270293fb9e04e5129befa7156117231e2a7a2ac282f083780445c3b04e

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page