mcpField
P
pyeconomics

pyeconomics

Local
pyeconomics.readthedocs.ioOther11Updated 1d ago
RepositoryVisit website

About pyeconomics

pyeconomics provides tested, cited economics and finance models and data for analysts, researchers, and developers. Its results include reproducible provenance manifests and are available through Python, CLI, REST, MCP, and export interfaces.

Key features

  1. 0150 economics and finance model families
  2. 02Data from 31 providers
  3. 03Typed inputs with units and bounds
  4. 04Provenance manifest for each result
  5. 05Python, CLI, REST, and MCP access
  6. 06Tabular and reproducibility-bundle exports

Use cases

  1. 01Run cited finance and economics models
  2. 02Retrieve data concepts with live bindings
  3. 03Reproduce and audit model results

MCP support

The optional MCP server provides access to the pyeconomics models and data for MCP clients. Install MCP support with the documented extra or run the server using `uvx`.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "pyeconomics-dev-pyeconomics": {
      "command": "uvx",
      "args": [
        "pyeconomics"
      ]
    }
  }
}
Run commanduvx pyeconomics

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypipyeconomics1.0.0b1

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

pyeconomics: Empowering Economic Insight

pyeconomics

CI PyPI Licence OpenSSF Scorecard

Status: 1.0.0b1 is a beta pre-release on PyPI. Install explicitly with pip install --pre pyeconomics==1.0.0b1 (Python 3.12 or later). Plain pip install pyeconomics still installs 0.2.6, the stable release. Pre-releases carry no stability promise until 1.0.0.

pyeconomics provides 50 tested, cited economics and finance model families across 13 domains: foundations, fixed income, derivatives, international, equity, corporate, accounting, portfolio, performance, risk, econometrics, macroeconomics and asset pricing. The data platform adds 31 providers, 171 catalog concepts and live bindings with real-time vintages. Every model is served identically through the Python API, the pyeconomics command line, the REST API (pyeconomics serve), the MCP server (pyeconomics mcp) and tabular or reproducibility-bundle exports. Typed inputs declare units and bounds; every result carries a reproducible provenance manifest. Rates and percentages are decimals: 0.05 means 5%.

Use the 1.0 documentation preview for formulas, assumptions and examples, and the beta release notes for the shipped surfaces and known limitations. See the CLI guide, REST API guide, MCP server guide, exports guide, AI narrative guide, data guide and keys guide to get started. Install optional econometrics, plotting, REST API and MCP support with pip install --pre "pyeconomics[econometrics,plot,server,mcp]==1.0.0b1", or run the MCP server directly with uvx --from "pyeconomics[mcp]==1.0.0b1" pyeconomics mcp.

This beta replaces the 0.2.x API and adds the command line, exports and reproducibility bundles, REST API, MCP server and optional AI narrative on top of the model engine and data platform. The web app arrives in Phase 5; the project roadmap and architecture decisions record that plan. Keep legacy workloads in a separate environment.

pyeconomics 0.2.x

0.2.6 is the current stable release of the 0.2.x line: four monetary-policy rules over FRED data.

  • It is MIT-licensed. Its source lives on the legacy/0.2.x branch, and its documentation at https://pyeconomics.readthedocs.io/.
  • It receives security fixes only, and reaches end of life when 1.0.0 is released. Pins such as pyeconomics<1 keep working.
  • 0.2.0 to 0.2.5 log the FRED API key at DEBUG level. Upgrade to 0.2.6 and rotate any key those versions used: see advisory GHSA-j6rp-vwwv-jrr8.

Not to be confused with

This project is not davidrpugh/pyeconomics (computational-economics course code from 2013–14) or pyecon.org (a site teaching Python for economics). The three share only the name.

Contributing and security

Licence

From 1.0, pyeconomics is licensed under the Apache License 2.0; see also NOTICE. Releases up to and including 0.2.x remain MIT-licensed.

Notices

As is; not investment advice. pyeconomics is for educational and informational use only, and is not registered with any regulator.

CFA® and Chartered Financial Analyst® are trademarks owned by CFA Institute. pyeconomics is not affiliated with, endorsed by, or a Prep Provider of CFA Institute.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.