edge — security grade SAFE, quality 62/100

Security audit verdict: SAFE · quality 62/100

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 todoforai · MCP Server · ★ 91

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

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

About edge

TODO for AI Edge The Web connector for TODO for AI — connects your machine to the TODO for AI server and gives TODOs shell, file, and browser access to get things done locally. Handles file operations, shell execution, DOCX/XLSX editing, and more. For an overview, prebuilt binaries (Windows, macOS, Linux), and what the connector enables, see the Edge download page. Quickstart Already have Node? works too. On Windows: . First run opens your browser for device-flow login and saves the key to the platform credentials store ( on Linux, on macOS, on Windows; legacy still read). Shared with the bridge and CLI. No flags needed. Other ways to authenticate Get a key at todofor.ai/apikey. From source Compile standalone binary bash cd bun bun build src/index.t

agent-runtimeai-agentai-todo-listautonomous-agentbrowser-automationclaudeclicoding-agentcomputer-usegemini

Quick Facts

Stars91
Forks1
LanguageTypeScript
CategoryMCP Server
Quality Score62.200388779584/100
Last Updated2026-10-04
Created2025-03-11
Platformsbrowser, claude-code, cli, gemini, mcp, node
Est. Tokens~14k

Compatible Skills

These tools work well together with edge for enhanced workflows:

  • kordoc — semantic(0.33)+complementary+same_lang+shared_platform (52%)

edge alternative? Top 6 similar tools

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

  • cognithor by Alex8791-cyber · ⭐ 153

    Cognithor · Agent OS: Local-first autonomous agent operating system. 19 LLM providers, 18 channels, 145 MCP to

  • OSA by Miosa-osa · ⭐ 76

    An AI agent for your terminal, built on signal theory: every output is signal, not noise. Codes, runs multi-st

  • c4-genai-suite by codecentric · ⭐ 173

    c4 GenAI Suite

  • openclaw-command-center by jontsai · ⭐ 246

    🤖 AI assistant command and control dashboard — Spawn more Overlords!

  • omega-memory by omega-memory · ⭐ 219

    Persistent memory for AI coding agents

  • palot by ItsWendell · ⭐ 190

    Just another desktop client for OpenCode 2. Manage projects, sessions, parallel agents, requests, and changes

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is edge?

edge is Open-source AI agent that runs on your own computer and does your tasks. Any model (Claude, GPT, Gemini, Grok, Ollama), drives your real browser, shell, files, DOCX/XLSX.. It is categorized as a MCP Server with 91 GitHub stars.

What programming language is edge written in?

edge is primarily written in TypeScript. It covers topics such as agent-runtime, ai-agent, ai-todo-list.

How do I install or use edge?

You can find installation instructions and usage details in the edge GitHub repository at github.com/todoforai/edge. The project has 91 stars and 1 forks, indicating an active community.

What are the best alternatives to edge?

The top alternatives to edge on Agent Skills Hub include cognithor, OSA, c4-genai-suite. 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