O360 MCP server
com.offensive360/o360-mcp·v1.0.2Run Offensive360 SAST scans (60+ languages) on local code; findings with file/line and fixes
0 stars23 downloads/wk
Reviews
Write oneNobody has reviewed O360 yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
O360 tools (2, 1 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
o360_scan_pathwrite actionRun an Offensive360 SAST scan on a local directory (60+ languages, taint/data-flow analysis).
o360_scan_statusCheck the queue position of an Offensive360 scan started with o360_scan_path.
Public scan report
scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it
- Code scan2 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 53 days ago12/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10
How O360 compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 80/100
- higher than 60% of 48,255 servers
- Tools
- 2
- the typical server has 7
- Tools that change things
- 50%
- typical: 0%. Fewer write tools means less an agent can break
- Downloads a week
- 23
- more than 9% of 12,191 servers with a package
What its tools let an agent do: 1 read · 1 change
Install O360 in Claude Code, Cursor or VS Code
Runs npx -y o360-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add o360-mcp -- npx -y o360-mcp
What the publisher says
From the O360 repository's README, as published. We do not edit it. Read it on GitHub
Offensive360 MCP Server
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:
Ask your assistant things like "scan this project with Offensive360 and fix the criticals" — it scans, reads the findings, and starts patching.
Setup
You need an Offensive360 External scan token:
offensive360.com/free-for-open-source
- Open-source / public repos: free — request one at
- Commercial: any admin of your instance can create one under Settings → Tokens
Claude Code
claude mcp add offensive360 \
-e O360_URL=https://sast.offensive360.com \
-e O360_TOKEN=<your-token> \
-- npx -y o360-mcpClaude Desktop / Cursor (JSON)
{
"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.
Notes
The default client timeout is 900s (timeout_seconds parameter to override).
- Scans are synchronous; typical duration is 1–5 minutes depending on codebase size.
upload automatically; add more via the exclude parameter.
- Common junk directories (node_modules, .git, dist, …) are excluded from the
- Findings are also visible in your Offensive360 dashboard with full data-flow traces.
- Requires Node 18+.
About Offensive360
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
Nothing above is checked by us. What we check is on the safety report.
O360: common questions
- Is O360 MCP server safe?
- Mostly: it is graded B (80/100). Read the O360 safety report
- How do I install O360?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does O360 need an API key?
- Yes. The registry entry asks for
O360_TOKEN. - Is O360 maintained?
- The last commit was 94 days ago (2026-08-02). The latest release is v1.0.2.
- How does O360 compare with other MCP servers?
- safety score 80/100 (higher than 60% of 48,255 servers); tools 2 (the typical server has 7); tools that change things 50% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.