ktg-plugin-marketplace/plugins/llm-security/scanners/mcp-baseline-reset.mjs
Kjell Tore Guttormsen 001df2ebe8 feat(commands): E14 part 3 — /security mcp-baseline-reset slash command
Wave C step C3: closes E14 with the user-facing reset command.

After a legitimate MCP server upgrade the sticky baseline (added in C1)
becomes a stale "what the tool used to say" anchor and every subsequent
post-mcp-verify advisory will re-flag the change. /security mcp-baseline-reset
lets the user acknowledge the upgrade so the next call seeds a fresh
baseline.

New files:
- scanners/mcp-baseline-reset.mjs — small CLI wrapper around clearBaseline /
  listBaselines. Modes: --list (read-only), --target <name>, no-args (all).
  Outputs JSON summary on stdout. Exit 0 always (idempotent).
- commands/mcp-baseline-reset.md — dispatcher following mcp-inspect.md
  shape. Frontmatter: name=security:mcp-baseline-reset, sonnet model,
  Read/Bash/AskUserQuestion tools. 4-step body (list -> confirm scope
  -> execute -> confirm result).
- tests/scanners/mcp-baseline-reset.test.mjs — 10 CLI tests across
  --list, --target, clear-all, idempotency, history preservation, and
  bare-positional sugar.

Updated:
- commands/security.md — new row in commands table after mcp-inspect.
- CLAUDE.md — new commands-table row + new v7.3.0 narrative section
  describing the baseline schema, cumulative-drift detection, reset
  semantics, and the LLM_SECURITY_MCP_CACHE_FILE override.
- Plugin README.md — new MCP-baseline-reset row in commands table,
  scanner count 12 standalone -> 13 standalone, new "MCP Description
  Drift (E14, v7.3.0)" subsection explaining the sticky baseline,
  cumulative threshold, reset semantics, and env-var override.
- Root marketplace README.md — scanner count 22 -> 23 (10 orchestrated +
  13 standalone), command count 19 -> 20, test count 1511 -> 1768.

Wave C complete: 1738 -> 1768 tests (+30 across C1/C2/C3). Per plan,
Wave C does NOT bump the plugin version — that lands at the wave-bundle
release. The advisory text in post-mcp-verify already references the
new command path so the user has a ready remediation step.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-04-30 16:49:01 +02:00

101 lines
2.8 KiB
JavaScript

#!/usr/bin/env node
// mcp-baseline-reset.mjs — Reset MCP description-cache baselines.
//
// Purpose:
// The description cache (scanners/lib/mcp-description-cache.mjs) anchors a
// sticky baseline per MCP tool so that cumulative drift can be detected
// across many small updates. After a legitimate MCP server upgrade the
// baseline becomes a stale "what the tool used to say" reference and must
// be reset so the next call seeds a fresh baseline.
//
// Modes:
// --list Read-only — list current baselines as JSON.
// --target <toolName> Clear baseline for one tool.
// (no args) Clear baselines for all tools.
//
// Output: JSON summary on stdout. Exit 0 always (idempotent).
//
// Used by /security mcp-baseline-reset slash command. Not part of
// scan-orchestrator.
import {
clearBaseline,
listBaselines,
loadCache,
} from './lib/mcp-description-cache.mjs';
function parseArgs(argv) {
const args = { list: false, target: null };
for (let i = 2; i < argv.length; i++) {
const a = argv[i];
if (a === '--list') {
args.list = true;
} else if (a === '--target' || a === '-t') {
args.target = argv[++i] || null;
} else if (a === '--help' || a === '-h') {
args.help = true;
} else if (!a.startsWith('--')) {
// bare positional treated as target for convenience
args.target = a;
}
}
return args;
}
function help() {
process.stdout.write(
'mcp-baseline-reset.mjs — Reset MCP description-cache baselines.\n\n' +
'Usage:\n' +
' node scanners/mcp-baseline-reset.mjs --list\n' +
' node scanners/mcp-baseline-reset.mjs --target <tool>\n' +
' node scanners/mcp-baseline-reset.mjs # clear all\n\n' +
'Output: JSON. Exit code 0 always.\n',
);
}
function emit(obj) {
process.stdout.write(JSON.stringify(obj, null, 2) + '\n');
}
function main() {
const args = parseArgs(process.argv);
if (args.help) {
help();
return 0;
}
if (args.list) {
const baselines = listBaselines();
emit({
mode: 'list',
count: baselines.length,
baselines: baselines.map((b) => ({
tool: b.tool,
baseline_excerpt: (b.baseline || '').slice(0, 120),
seen_at: b.seenAt,
last_seen: b.lastSeen,
history_events: b.history,
})),
});
return 0;
}
// Reset path
const result = clearBaseline(args.target || undefined);
// After clearing, count remaining baselines
const cache = loadCache();
let remaining = 0;
for (const entry of Object.values(cache)) {
if (entry && entry.baseline) remaining++;
}
emit({
mode: 'reset',
target: args.target || null,
cleared: result.cleared,
tools: result.tools,
remaining,
});
return 0;
}
process.exit(main());