StatsPAI — security grade SAFE, quality 63/100

Security audit verdict: SAFE · quality 63/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by brycewang-stanford · MCP Server · ★ 323

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is StatsPAI safe to install? View the security audit →

About StatsPAI

English | 中文 StatsPAI: Agent-Native Causal Inference & Econometrics Toolkit for Python [](https://doi

agent-nativeai-agentscausal-discoverycausal-inferencedata-sciencedifference-in-differencesdouble-machine-learningeconometricsinstrumental-variablesllm

Quick Facts

Stars323
Forks67
LanguagePython
CategoryMCP Server
LicenseMIT
Quality Score63.1666562408099/100
Last Updated2026-09-22
Created2025-07-26
Platformsmcp, python
Est. Tokens~25k

Compatible Skills

These tools work well together with StatsPAI for enhanced workflows:

  • DeepEye — semantic(0.18)+complementary+rare_topics+same_lang+similar_pop+shared_platform (61%)
  • stata-skill — semantic(0.34)+complementary+same_lang+similar_pop+shared_platform (57%)
  • stata-mcp — semantic(0.35)+rare_topics+same_lang+similar_pop+shared_platform (56%)
  • statsclaw — semantic(0.30)+complementary+rare_topics+similar_pop (56%)

StatsPAI alternative? Top 6 similar tools

Looking for a StatsPAI alternative? If you're comparing StatsPAI with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • finai-research by csmar432 · ⭐ 106

    Evidence-first AI workflow for economic and financial research: literature → identification → data → econometr

  • wisp-science by xuzhougeng · ⭐ 1.2k

    Open-source, local-first desktop AI research workbench for scientific computing with Python/R, MCP bioinformat

  • BambooAI by pgalko · ⭐ 791

    A Python library powered by Language Models (LLMs) for conversational data discovery and analysis.

  • maverick-mcp by wshobson · ⭐ 668

    MaverickMCP - Personal Stock Analysis MCP Server

  • web-agent-protocol by OTA-Tech-AI · ⭐ 509

    🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support

  • Containarium by FootprintAI · ⭐ 283

    Open-source agent runtime — SSH-native isolation, eBPF egress policy, Kubernetes + LXC backends, GPU passthrou

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is StatsPAI?

StatsPAI is StatsPAI is the first Agent-native Python library for causal inference and applied econometrics — unified API, broad cross-method coverage, structured result objects, machine-readable schemas, Skills,. It is categorized as a MCP Server with 323 GitHub stars.

What programming language is StatsPAI written in?

StatsPAI is primarily written in Python. It covers topics such as agent-native, ai-agents, causal-discovery.

How do I install or use StatsPAI?

You can find installation instructions and usage details in the StatsPAI GitHub repository at github.com/brycewang-stanford/StatsPAI. The project has 323 stars and 67 forks, indicating an active community.

What license does StatsPAI use?

StatsPAI is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to StatsPAI?

The top alternatives to StatsPAI on Agent Skills Hub include finai-research, wisp-science, BambooAI. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools