Kadent Scan
by kadent.so · remote · no sign-in to list tools · v1.0.0 · published by so.kadent
Free, read-only security scanner for remote MCP servers, before you connect them.
1 tool: 1 change things.
Scanned Oct 21, 2026
- Deletes or cancels0Claude Code: deny
- Can't be undone0Claude Code: ask
- Changes things1Claude Code: ask: see these tools
- Only reads0Claude Code: allow
1 check matched something in the tool definitions. No finding is not a safety guarantee. How the checks work.
claude mcp add --transport http kadent-scan https://mcp.kadent.so/scan/mcpFindings
Matches of fixed checks, with the text they matched.
- Warnscan_mcp_server
The server marks "scan_mcp_server" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":true}; The description's first verb is "run": a word for a change.
Tools
Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.
1 tool
Changes things 1Claude Code: ask
scan_mcp_serverRuns a free, read-only security scan of a remote MCP server before you connect it.1 finding
Why it is in this group
- The description's first verb is "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "scan_mcp_server" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":true}; The description's first verb is "run": a word for a change.
Description, as the server wrote it Runs a free, read-only security scan of a remote MCP server before you connect it. Performs an ordinary MCP handshake (never anything more invasive), lists the server's tools, rates each one's capabilities (private-data access, untrusted content, network egress, destructive actions), flags prompt-injection patterns in tool descriptions, and reports whether the lethal trifecta is reachable. Scan only servers you run or are entitled to connect to.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http kadent-scan https://mcp.kadent.so/scan/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [],
"ask": [
"mcp__kadent-scan__scan_mcp_server"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as kadent-scan. Review it before you use it.