Developer Tools
skillsafe.ai
Provides tools to search, recommend, install, and save AI coding skills from the SkillSafe registry.
ENDPOINT 1
https://api.skillsafe.ai/mcp
MCP server metadata
- Name
- skillsafe
- Version
- 1.0.0
Known tools 8
recommend_skillsGiven a task description, recommend the most relevant skills from the SkillSafe registry.
Inferred read-onlyget_skill_infoGet detailed metadata for a specific skill by namespace and name (e.g.
Inferred read-onlyscan_mcp_configScan MCP tool definitions or server configurations for poisoning patterns (injection tags, credential theft, stealth instructions, exfiltration).
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.skillsafe]
url = "https://api.skillsafe.ai/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"skillsafe": {
"type": "http",
"url": "https://api.skillsafe.ai/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: skillsafe
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": {
"url": "https://api.skillsafe.ai/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"skillsafe": {
"type": "http",
"url": "https://api.skillsafe.ai/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "skillsafe",
"transport": "streamable-http",
"url": "https://api.skillsafe.ai/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for skillsafe.ai was fetched 2026-08-04T15:53:32.986Z and is being refreshed.
skillsafe.ai is assessed as Neutral: No suspicious signals found, but no strong positive signal either
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.