magg — security grade SAFE, quality 64/100

Security audit verdict: SAFE · quality 64/100

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 sitbon · MCP Server · ★ 142

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

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

About magg

🧲 Magg - The MCP Aggregator [//]: # ([![Tests](https://img.shields.io/github/actions/workflow/status/sitbon/magg/test.yml?style=flat-square&label=tests)](https://github.com/sitbon/magg/actions/workflows/test.yml)) [![DeepWiki](https://img.shields.io/badge/DeepWiki-sitbon%2Fmagg-blue.svg?logo=data:image/png;base64,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

aggregatoraidockerdocker-composefastmcpjson-rpcllmmcpmcp-sdkmcp-server

Quick Facts

Stars142
Forks23
LanguagePython
CategoryMCP Server
LicenseAGPL-3.0
Quality Score63.6451559028057/100
Open Issues7
Last Updated2026-08-02
Created2025-06-20
Platformsdocker, mcp, python
Est. Tokens~17k

Compatible Skills

These tools work well together with magg for enhanced workflows:

  • pydantic-ai-todo — semantic(0.23)+complementary+rare_topics+same_lang+similar_pop+shared_platform (58%)
  • compose-for-agents — semantic(0.24)+complementary+rare_topics+similar_pop+shared_platform (48%)
  • Horizon — semantic(0.33)+rare_topics+same_lang+similar_pop+shared_platform (46%)

magg alternative? Top 6 similar tools

Looking for a magg alternative? If you're comparing magg 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.

  • MCP-PostgreSQL-Ops by call518 · ⭐ 161

    🐘 Give AI assistants full PostgreSQL DBA superpowers — 30+ tools for performance analysis, bloat detection, l

  • gopher-mcp by GopherSecurity · ⭐ 147

    C++ MCP SDK - build Model Context Protocol (MCP) servers and clients in C++ / CPP. Enterprise-grade security,

  • 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

  • mcp-graphql by blurrah · ⭐ 407

    Model Context Protocol server for GraphQL

  • mcp-server-odoo by ivnvxd · ⭐ 377

    Model Context Protocol (MCP) server that enables AI assistants to securely interact with Odoo ERP systems thro

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is magg?

magg is Magg: The MCP Aggregator. It is categorized as a MCP Server with 142 GitHub stars.

What programming language is magg written in?

magg is primarily written in Python. It covers topics such as aggregator, ai, docker.

How do I install or use magg?

You can find installation instructions and usage details in the magg GitHub repository at github.com/sitbon/magg. The project has 142 stars and 23 forks, indicating an active community.

What license does magg use?

magg is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to magg?

The top alternatives to magg on Agent Skills Hub include MCP-PostgreSQL-Ops, gopher-mcp, maverick-mcp. 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