LabscoMCP early access ↗
CSOAI-ORGMCP SERVER

MCP Prompt Injection Scanner

Scan for prompt-injection patterns using 30+ canonical detection rules across five severity tiers.

by CSOAI-ORG ↗Agent Guardrails, Content Safety & AuditCommunity

LABSCO SUMMARY

Severity tiers are what make a rule set usable.

Thirty rules that all shout equally loudly produce a report nobody reads; sorting them into five tiers is the difference between a scanner and a noise source. The repository documents the rule set and the threat class it targets. Its five tools scan another MCP server's tool list (from the server's address, or pasted in), list the rules, issue a signed safety report on paid plans and show pricing.

What it is

A Python server that scans for MCP injection. It ships 30+ canonical detection rules sorted into 5 severity tiers, aimed at the MCP remote-code-execution class described in April 2026 — so findings arrive ranked rather than as a flat list you have to triage.

What you get

Rule-based scanning with severity already attached: 30+ canonical rules across 5 tiers, so a high-severity hit is distinguishable from a stylistic one without reading every result.

Requirements

pip install meok_mcp_injection_scan_mcp, or add the PyPI package meok-mcp-injection-scan-mcp to your client over stdio. MIT-licensed.

Setup effort

One command — pip install meok_mcp_injection_scan_mcp