MCP client integration · mcp-sentinel-scanner
Evidence, inside
your MCP client.
Bring Sentinel's 184-rule catalogue into Claude, Cursor, or another MCP client. Supply server metadata or enumerate a live endpoint, then inspect the findings, evidence, and coverage-aware verdict.
npx mcp-sentinel-scannerThe client integration analyzes supplied inputs and lists a live server's declared surface. It does not invoke tools on that target.
Quick Setup
Add to Claude Desktop
Open your Claude Desktop config and add the scanner as an MCP server:
{
"mcpServers": {
"mcp-sentinel-scanner": {
"command": "npx",
"args": ["-y", "mcp-sentinel-scanner"]
}
}
}Ask Claude to scan
Just ask in natural language. The scanner exposes three tools that Claude can call:
Get actionable results
Every finding includes evidence (what triggered it) and remediation (how to fix it).
Available Tools
scan_server
Analyze server metadata without a live connection. Pass tools, descriptions, source code, and dependencies. Returns findings + verdict.
scan_endpoint
Connect to a live MCP server endpoint. Enumerates tools via initialize + tools/list (safe, read-only), then runs all 184 detection rules.
list_rules
List all available detection rules. Filter by category or severity to explore specific rule sets.
Example Output
What a scan result looks like:
{
"server_name": "my-mcp-server",
"verdict": "risk",
"verdict_summary": "Risk - a critical issue (or a lethal-trifecta
capability pattern) was observed across 3 findings.",
"lethal_trifecta": false,
"severity_counts": {
"critical": 1,
"high": 1,
"medium": 1,
"low": 0,
"informational": 0
},
"findings_count": 3,
"findings": [
{
"rule": "Prompt Injection in Tool Description",
"severity": "critical",
"evidence": "Tool description contains injection pattern:
'ignore all previous instructions'",
"remediation": "Remove instruction-like language from
tool descriptions. Use factual, concise descriptions.",
"rule_id": "A1"
},
{
"rule": "Hardcoded Secrets",
"severity": "high",
"evidence": "Hardcoded API key pattern detected:
sk-proj-abc123...",
"remediation": "Move secrets to environment variables.
Never hardcode API keys in source code.",
"rule_id": "C5"
},
{
"rule": "Missing Input Validation",
"severity": "medium",
"evidence": "Parameter 'query' has type string with
no maxLength, pattern, or enum constraint.",
"remediation": "Add maxLength, pattern, or enum
constraints to string parameters.",
"rule_id": "B1"
}
],
"rules_version": "2026.09"
}Verdict Interpretation
A scan leads with a coverage-aware verdict, not a number. A clean result is only Safe when coverage was sufficient for that verdict - otherwise it is Insufficient coverage, never Safe.
Detection Coverage
184 rules across 21 categories - counts derived from the live rule catalogue
Safety
This MCP client integration never invokes tools on target servers. It initializes the connection and uses the read-only list methods for enumeration. Its analysis is deterministic and does not use a language model. Findings still need review, and the verdict is limited by the inputs available.
Other MCP Clients
Works with any MCP-compatible client:
Settings → MCP → Add Server.vscode/mcp.json~/.codeium/windsurf/mcp_config.jsonclaude mcp add mcp-sentinel-scanner02 / Follow the finding
A verdict opens the question.
Evidence lets you examine it.
Inspect the rule, its supplied inputs, and the evidence behind each finding. Keep completed execution separate from checks that could not run.
The same rule catalogue serves different input shapes. Coverage belongs to the actual assessment, rather than to the number of rules available.
The MCP client integration enumerates a live target; it never invokes that target's tools.
Read the evidence guideA result is a starting point
Follow the finding to its source.
Understand what each rule examines, which inputs it needs, and how its findings relate to security controls.