Server data from the Official MCP Registry
Shape-shifting MCP hub — shapeshift() into 130,000+ servers at runtime. No restarts. 7 registries.
Shape-shifting MCP hub — shapeshift() into 130,000+ servers at runtime. No restarts. 7 registries.
Kitsune is a well-architected MCP hub with thoughtful security design and clear permission scoping appropriate to its purpose as a dynamic server loader. Authentication and credential handling are sound with env-var isolation and PKCE OAuth support. However, three moderate concerns exist: (1) process spawning (npx/uvx/docker) is inherently dangerous and relies entirely on user confirmation and trust flags for safety, (2) network access to 7 registries plus arbitrary HTTP servers is broad but documented, and (3) there is potential for confused-deputy attacks if a mounted server can craft malicious credentials. The codebase is well-tested and avoids common pitfalls, but the attack surface introduced by dynamic loading and process spawning warrants user awareness. Supply chain analysis found 9 known vulnerabilities in dependencies (1 critical, 6 high severity). Package verification found 2 issues.
4 files analyzed · 18 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Set these up before or after installing:
Environment variable: SMITHERY_API_KEY
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-kaiser-data-kitsune-mcp": {
"env": {
"SMITHERY_API_KEY": "your-smithery-api-key-here"
},
"args": [
"-y",
"kitsune-mcp"
],
"command": "npx"
}
}
}Be the first to review this server!
by Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.