Skillget

aigroup-econ-mcp

mcp
Security Audit
Warn
Health Warn
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 8 GitHub stars
Code Pass
  • Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested
Purpose
This server provides a comprehensive suite of 66 econometrics and statistical analysis tools. It allows AI assistants to perform structured quantitative tasks like regression, causal inference, time series modeling, and machine learning workflows.

Security Assessment
The overall security risk is rated as Low. A light code scan of 12 files revealed no dangerous patterns, hardcoded secrets, or requests for dangerous permissions. Because it acts as a server for data analysis, it inherently processes whatever data you pass to it, but it does not appear to execute hidden shell commands or make unauthorized external network requests.

Quality Assessment
The project is under active development, with its last push occurring today. It is properly licensed under the permissive MIT license and features a detailed, professional README. However, community trust and visibility are currently low. With only 8 GitHub stars and an unknown number of compatible CLI integrations, it is still a very new or niche project. Developers should expect limited community support or external documentation beyond what the original author provides.

Verdict
Use with caution — the code appears clean and safe, but the project currently lacks a broad, established community to validate its reliability.
SUMMARY

Econometrics MCP server for regression, causal inference, time series, panel data, and statistical analysis workflows.

README.md

aigroup-econ-mcp

License: MIT
Python
Version
Tools

Econometrics MCP server for regression, causal inference, time series, panel data, machine learning, and broader statistical analysis workflows.

Overview

aigroup-econ-mcp is a professional econometrics-oriented MCP server designed to help AI assistants and MCP clients perform structured quantitative analysis.

It covers:

  • parameter estimation and regression analysis
  • causal inference workflows
  • microeconometrics and panel data
  • time series and volatility models
  • machine learning for econometric tasks
  • spatial econometrics, decomposition, and inference tools

Highlights

  • 66 professional tools across core econometrics domains
  • Multiple input formats including CSV, JSON, TXT, and Excel
  • Multiple output formats including JSON, Markdown, HTML, LaTeX, and text
  • Support for MCP clients such as RooCode, Claude-compatible tools, and other MCP hosts
  • Broad method coverage from OLS and IV to ARIMA, GARCH, GAM, and causal forests
  • Designed for research and applied analysis rather than narrow single-task workflows

Tool Groups

The server currently groups its 66 tools across the following categories:

  • Basic parametric estimation — OLS, MLE, GMM
  • Causal inference — DID, IV, PSM, fixed/random effects, RDD, synthetic control, event study, and more
  • Decomposition analysis — Oaxaca-Blinder, ANOVA, time-series decomposition
  • Machine learning — random forest, gradient boosting, SVM, neural networks, clustering, DML, causal forest
  • Microeconometrics — logit, probit, multinomial logit, Poisson, negative binomial, Tobit, Heckman
  • Missing data handling — simple imputation and MICE
  • Model diagnostics and robust inference — specification tests, GLS, WLS, robust errors, regularization, simultaneous equations
  • Nonparametric methods — kernel regression, quantile regression, spline regression, GAM
  • Spatial econometrics — weights matrices, Moran's I, Geary's C, LISA, spatial regression, GWR
  • Statistical inference — bootstrap and permutation tests
  • Time series and panel data — ARIMA, exponential smoothing, GARCH, unit-root tests, VAR/SVAR, cointegration, dynamic panel, panel VAR, structural breaks, time-varying parameter models

Quick Start

Requirements

  • Python >= 3.10
  • uvx recommended for easiest usage, or pip

Run with uvx

uvx aigroup-econ-mcp

If uvx keeps using an older cached build:

uvx --no-cache aigroup-econ-mcp

Install with pip

pip install aigroup-econ-mcp
aigroup-econ-mcp

MCP Client Configuration

Claude-compatible MCP clients / RooCode / similar tools

{
  "mcpServers": {
    "aigroup-econ-mcp": {
      "command": "uvx",
      "args": ["aigroup-econ-mcp"]
    }
  }
}

Input & Output Support

Supported input formats

  • CSV
  • JSON
  • TXT
  • Excel (.xlsx, .xls)

Typical usage patterns:

  • direct structured data input
  • raw file content input
  • local file path input

Supported output formats

  • json
  • markdown
  • html
  • latex
  • text

Example Use Cases

  • OLS and generalized regression modeling
  • difference-in-differences and instrumental variable analysis
  • matching and regression discontinuity workflows
  • random forest / gradient boosting / causal forest analysis
  • ARIMA, GARCH, VAR, and cointegration modeling
  • panel diagnostics and dynamic panel estimation

Project Structure

aigroup-econ-mcp/
├── aigroup_econ_mcp/       # MCP server + CLI
│   ├── cli.py              #   argparse entry point
│   ├── server.py           #   FastMCP wire-up
│   ├── registry.py         #   ToolSpec registry
│   ├── _registrations.py   #   all 66 tools registered here
│   └── errors.py
├── tools/                  # adapter layer (I/O + formatting)
├── econometrics/           # algorithms
├── resources/
├── prompts/
├── docs/
│   ├── ARCHITECTURE.md
│   ├── PUBLISHING.md
│   └── TESTING.md
├── tests/
├── CHANGELOG.md
└── pyproject.toml

See docs/ARCHITECTURE.md for layer boundaries and how
to add a new tool.

Development

uv sync
uv run pytest

Useful development commands:

uv run black .
uv run isort .

Troubleshooting

uvx resolves an old version

uvx caches per-version, so if a published release is not picked up:

uvx --refresh aigroup-econ-mcp
# or
uv cache clean

License & Usage

This project is released under the MIT License.

You may use, copy, modify, merge, publish, distribute, sublicense, and sell copies of this software, including in academic, research, internal, and commercial environments, provided that the original copyright notice and license text are preserved.

Please keep in mind:

  • the software is provided "AS IS", without warranty of any kind
  • you must retain the relevant copyright and permission notice in copies or substantial portions of the software
  • statistical results still depend on data quality, assumptions, and correct methodological choices by the user

See the full text in LICENSE.

Acknowledgments

Core Scientific Ecosystem

  • statsmodels — statistical modeling foundations
  • pandas — data manipulation and tabular workflows
  • scikit-learn — machine learning components
  • linearmodels — panel data and econometric modeling support
  • arch — volatility and ARCH/GARCH modeling

Community & Protocol Ecosystem

  • Model Context Protocol — MCP integration model
  • The broader econometrics and open-source scientific computing community

Support

Reviews (0)

No results found