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 punkpeye · MCP Server · ★ 229
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is awesome-remote-mcp-servers safe to install? View the security audit →
Awesome Remote MCP Servers [!IMPORTANT] ray.run – from idea to a production-grade MCP server in under a minute! 🦜 Ad A curated list of remote Model Context Protocol (MCP) servers — hosted endpoints you connect to over a URL. No install, no runtime, no local process. Looking for servers you run yourself? See awesome-mcp-servers. What is a remote MCP server? How to connect Legend Servers Community Contributing What is a remote MCP server? A remote MCP server is an MCP server someone else operates for you. Instead of installing a package and spawning a local process over stdio, you point your client at a URL and authenticate — usually with OAuth. the provider's infra
| Stars | 229 |
| Forks | 328 |
| Category | MCP Server |
| License | MIT |
| Quality Score | 61.7428703176462/100 |
| Open Issues | 104 |
| Last Updated | 2026-09-15 |
| Created | 2026-09-08 |
| Platforms | mcp |
| Est. Tokens | ~27k |
These tools work well together with awesome-remote-mcp-servers for enhanced workflows:
Explore other popular mcp server tools:
awesome-remote-mcp-servers is A collection of remote MCP servers.. It is categorized as a MCP Server with 229 GitHub stars.
You can find installation instructions and usage details in the awesome-remote-mcp-servers GitHub repository at github.com/punkpeye/awesome-remote-mcp-servers. The project has 229 stars and 328 forks, indicating an active community.
awesome-remote-mcp-servers 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: