VibeSafe security scanner as an MCP server — scan code, live URLs, and run a Launch Check on your app from any MCP client (Claude, Cursor, etc.).
Vibesafe MCP server exists for a simple reason — assistants are far more useful when they can act on Vibesafe directly instead of describing what you should do. VibeSafe security scanner as an MCP server — scan code, live URLs, and run a Launch Check on your app from any MCP client (Claude, Cursor, etc.).
Run the VibeSafe security scanner directly inside any MCP client — Claude Desktop, Cursor, Windsurf, and others. Ask your AI to "scan this file with VibeSafe" and get a plain-English security report with fixes, without leaving your chat.
Once Vibesafe is connected, these are the calls the assistant has available:
vibesafe_scan_code — Scan code for exposed secrets, injection flaws, and risky patterns → security score + per-issue fixesvibesafe_scan_url — Scan a deployed site for missing security headers, HTTPS issues, exposed paths, CORS problemsvibesafe_launch_check — Open your deployed app in a real browser like a user, capture errors, return a launch-readiness scoreSetup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.
You will need one environment variable: VIBESAFE_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Vibesafe's toolset — vibesafe_scan_code, vibesafe_scan_url, vibesafe_launch_check — is a fair guide to whether it matches your workflow. It is maintained by sabahatghauri; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Vibesafe's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| vibesafe_scan_code | Scan code for exposed secrets, injection flaws, and risky patterns → security score + per-issue fixes |
| vibesafe_scan_url | Scan a deployed site for missing security headers, HTTPS issues, exposed paths, CORS problems |
| vibesafe_launch_check | Open your deployed app in a real browser like a user, capture errors, return a launch-readiness score |
{
"mcpServers": {
"vibesafe": {
"command": "npx",
"args": ["-y", "vibesafe-mcp"],
"env": {
"VIBESAFE_API_KEY": "vibesafe_sk_your_key_here"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| VIBESAFE_API_KEY | Credential the server authenticates with. | Yes |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.