About vibescan-mcp-server
vibescan-mcp-server exposes VibeScan security checks to Claude Code and other MCP clients. It scans projects locally for leaked secrets, risky code patterns, and Git hygiene issues, so project code stays on the machine.
Key features
- 01Scan for secrets and risky patterns
- 02Check Git hygiene issues
- 03List 17 detection rules
- 04Run scans locally
Use cases
- 01Check a project for leaked credentials
- 02Review code for dangerous execution patterns
- 03Find unignored environment or key files
MCP support
Exposes the `vibescan_scan` project-scanning tool and `vibescan_rules` rule-listing tool to MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEvibescan-mcp-server
mcp-name: io.github.Aguantar/vibescan-mcp-server
MCP server for VibeScan — scan projects for leaked secrets and security issues directly from Claude Code.
Features
vibescan_scan— Scan a project for secrets, dangerous patterns, and git hygiene issuesvibescan_rules— List all 17 detection rules
What VibeScan detects
- 14 secret categories: env files, config hardcodes, cloud credentials, Docker/infra, CI/CD pipelines, IDE settings, SSH keys, hardcoded patterns, frontend env vars, data files, doc secrets, mobile files, system configs, editor remnants
- Dangerous code patterns: eval(), exec(), shell injection, SQL injection, pickle, innerHTML
- Git hygiene: missing .gitignore, unignored .env/.pem/.key files
All scanning runs locally — your code never leaves your machine.
Installation
pip install vibescan-mcp-server
Usage with Claude Code
Add to your .mcp.json:
{
"mcpServers": {
"vibescan": {
"command": "vibescan-mcp-server"
}
}
}
Then ask Claude: "scan this project for security issues" or "check for leaked secrets".
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.