INDIVIDUAL MCP TOOL

scan_mcp_config

Scan MCP tool definitions or server configurations for poisoning patterns (injection tags, credential theft, stealth instructions, exfiltration).

skillsafe.ainone authenticationAvailability not checked

Input schema

{}

Inferred read-only · medium confidence · heuristic, not a guarantee.

CONNECT WITH APPROVAL

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.skillsafe-ai]
url = "https://api.skillsafe.ai/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "skillsafe-ai": {
      "type": "http",
      "url": "https://api.skillsafe.ai/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: skillsafe-ai
Remote MCP URL: https://api.skillsafe.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "skillsafe-ai": {
      "url": "https://api.skillsafe.ai/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "skillsafe-ai": {
      "type": "http",
      "url": "https://api.skillsafe.ai/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "skillsafe-ai",
  "transport": "streamable-http",
  "url": "https://api.skillsafe.ai/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

search_skills — Search the SkillSafe registry for AI coding skills.
recommend_skills — Given a task description, recommend the most relevant skills from the SkillSafe registry.
get_skill_info — Get detailed metadata for a specific skill by namespace and name (e.g.
install_skill — Install a skill from the SkillSafe registry.
save_skill — Save a skill to the SkillSafe registry.
share_skill — Create a share link for a saved skill version.
scan_skill — Scan skill files for security issues.