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 dnakov · MCP Server · ★ 121
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is claude-mcp safe to install? View the security audit →
MCP for Claude.ai A browser extension that enables MCP (Model Control Protocol) capabilities in Claude.ai, allowing you to connect Claude to external tools and services directly from the browser. This enables functionality that's already existing in claude.ai but not enabled. Features Connect Claude.ai to MCP-compatible servers Manage multiple server connections Configure environment variables and command-line arguments Debug logging options Dark mode support Installation From Source Clone this repository Install dependencies Build the extension Load the extension in your browser: Chrome/Edge: Go to Enable "Developer mode" Click "Load unpacked" Select the folder from this repository Firefox: Go to Click "Load Temporary Add-on" Select the file from the folder Usage Click on the extension icon in your browser toolbar when on claude.ai Add a new MCP server con
| Stars | 121 |
| Forks | 15 |
| Language | JavaScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 70.9118289365971/100 |
| Open Issues | 5 |
| Last Updated | 2025-06-18 |
| Created | 2025-04-12 |
| Platforms | browser, claude-code, mcp, node |
| Est. Tokens | ~6k |
These tools work well together with claude-mcp for enhanced workflows:
Explore other popular mcp server tools:
claude-mcp is Browser extension to enable MCP in claude.ai. It is categorized as a MCP Server with 121 GitHub stars.
claude-mcp is primarily written in JavaScript.
You can find installation instructions and usage details in the claude-mcp GitHub repository at github.com/dnakov/claude-mcp. The project has 121 stars and 15 forks, indicating an active community.
claude-mcp 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: