Brightsite Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Brightsite Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
The official Model Context Protocol server for BrightSite — connect AI assistants like Claude to manage your websites, pages, blog posts, components, forms, media, and analytics.
https://onbrightsite.com/api/mcpTransport: Streamable HTTP.
The server supports two authentication methods. Most modern MCP clients will negotiate OAuth automatically; clients that don't can fall back to a Bearer token.
OAuth-capable clients (Claude.ai, ChatGPT, Claude Desktop with OAuth, etc.) discover the auth flow automatically via /.well-known/oauth-protected-resource. Dynamic Client Registration (RFC 7591) is supported — no manual app setup needed.
For clients that don't support OAuth, generate a personal API key:
bs_...){
"mcpServers": {
"brightsite": {
"url": "https://onbrightsite.com/api/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}This server is published to the MCP Registry as io.github.brightsitehq/brightsite. The canonical metadata is in server.json.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.