
MCP server that runs SAST scans on local codebases and returns findings with severity and fixes, enabling AI assistants to perform security analysis and remediation.
Run Offensive360 SAST scans from inside your AI assistant. This Model Context Protocol server gives Claude Code, Claude Desktop, Cursor, and any other MCP client two tools:
| Tool | What it does |
|---|---|
o360_scan_path | Zips a local directory, runs a full SAST scan (60+ languages, taint/data-flow analysis), returns findings with file/line, severity, and fixes |
o360_scan_status | Queue position of a running scan |
Ask your assistant things like "scan this project with Offensive360 and fix the criticals" — it scans, reads the findings, and starts patching.
You need an Offensive360 External scan token:
claude mcp add offensive360 \
-e O360_URL=https://sast.offensive360.com \
-e O360_TOKEN=<your-token> \
-- npx -y o360-mcp
{
"mcpServers": {
"offensive360": {
"command": "npx",
"args": ["-y", "o360-mcp"],
"env": {
"O360_URL": "https://sast.offensive360.com",
"O360_TOKEN": "<your-token>"
}
}
}
}
O360_URL can point at your own on-premise or air-gapped instance — the server
talks only to the instance you configure.
timeout_seconds parameter to override).node_modules, .git, dist, …) are excluded from the
upload automatically; add more via the exclude parameter.One platform for SAST, DAST, MAST, SCA, malware & binary analysis, and license compliance — flat pricing, cloud or fully air-gapped on-premise. offensive360.com · Book a demo