
Guardrails for AI-written JS/TS: scans, weakened-test checks, package checks, verify before done.
Public tool metadata for what this MCP can expose to an agent.
ai_guard_scan_fileScan a single JS/TS file with structured findingsScan a single JS/TS file with structured findings
No parameter schema in public metadata yet.
ai_guard_scan_diffScan changed files in git diff (including newly created untracked JS/TS files)Scan changed files in git diff (including newly created untracked JS/TS files)
No parameter schema in public metadata yet.
ai_guard_scan_projectScan a bounded workspace directory (current source; not yet published)Scan a bounded workspace directory (current source; not yet published)
No parameter schema in public metadata yet.
ai_guard_rulesList rules and presets, or look up specific rules (`rules: ["no-floating-promise"]`) with remediation and docs linkList rules and presets, or look up specific rules (`rules: ["no-floating-promise"]`) with remediation and docs link
No parameter schema in public metadata yet.
ai_guard_check_integrityReport checks weakened by current Git changes (new suppressions, skipped/removed tests, lowered configs, removed CI steps), with `tier` and `hasBlockingFindings`Report checks weakened by current Git changes (new suppressions, skipped/removed tests, lowered configs, removed CI steps), with `tier` and `hasBlockingFindings`
No parameter schema in public metadata yet.
Sponsors
Deterministic AST safety layer and CI guardrails for AI-assisted JavaScript and TypeScript code.
Website • npm Package • GitHub Repository • Rules Catalog • Benchmarks • Claude Code • Documentation
eslint-plugin-ai-guard