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 indragiek · MCP Server · ★ 804
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is Context safe to install? View the security audit →
Context A beautiful, fully native macOS client for the Model Context Protocol (MCP) that empowers developers to interact with and debug their MCP servers. Overview Context is a native macOS app that makes it easy to test and debug MCP servers. It provides a visual interface to invoke tools, preview resources, and monitor logs in real-time. Built specifically for MCP server developers, it supports multiple simultaneous connections and provides the debugging visibility you need during development. While the current feature set covers the essentials, Context is actively being developed into a comprehensive MCP debugging suite. Future releases will include more complete MCP specification support, advanced debugging tools like tracing and proxying, and an integrated chat client that can access all functionality exposed by MCP servers.
| Stars | 804 |
| Forks | 36 |
| Language | Swift |
| Category | MCP Server |
| License | MIT |
| Quality Score | 57.1075867013415/100 |
| Open Issues | 12 |
| Last Updated | 2026-02-11 |
| Created | 2025-06-26 |
| Platforms | cli, mcp |
| Est. Tokens | ~3289k |
These tools work well together with Context for enhanced workflows:
Explore other popular mcp server tools:
Context is Native macOS client for Model Context Protocol (MCP). It is categorized as a MCP Server with 804 GitHub stars.
Context is primarily written in Swift.
You can find installation instructions and usage details in the Context GitHub repository at github.com/indragiek/Context. The project has 804 stars and 36 forks, indicating an active community.
Context is released under the MIT license, making it free to use and modify according to the license terms.
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: