{"name":"io.github.AIops-tools/ai-guardian","slug":"aiops-tools-ai-guardian","title":"AI Guardian","description":"Governed local-LLM observability: model policy, prompt scanner, capture proxy, 21 tools.","url":"https://mcp.market/server/aiops-tools-ai-guardian","rating":null,"grade":"A","score":91,"certified":false,"status":"active","category":"ai","tags":["ai"],"presence":{"score":29,"stars":0,"forks":0,"downloads_week":583,"last_push_at":"2026-09-16T12:54:16.000Z","license":"MIT"},"uptime":null,"claimed":false,"transport":"pypi","callable_via_gateway":false,"default_price_micros":0,"repository":"https://github.com/AIops-tools/AI-Guardian","website":null,"version":"0.11.3","remotes":[],"packages":[{"registryType":"pypi","identifier":"ai-guardian-aiops","version":"0.11.3","transport":{"type":"stdio"}}],"tools":[{"name":"anomaly_report","description":"[READ] Rollup: shadow models, digest drift, high-risk prompts, blocked count.","write_action":false,"price_micros":0,"input_schema":null},{"name":"guarded_generate","description":"[WRITE][risk=medium] Scan + policy-gate a prompt, record it, then run if allowed.","write_action":false,"price_micros":0,"input_schema":null},{"name":"list_models","description":"[READ] Installed models, each annotated with the allow/deny policy verdict.","write_action":false,"price_micros":0,"input_schema":null},{"name":"main","description":"Run the MCP server over stdio.","write_action":true,"price_micros":0,"input_schema":null},{"name":"model_details","description":"[READ] License / parameters / capabilities for one model.","write_action":false,"price_micros":0,"input_schema":null},{"name":"model_provenance","description":"[READ] Compare each installed model's digest against its pin; flag drift.","write_action":false,"price_micros":0,"input_schema":null},{"name":"observe_chat","description":"[WRITE][risk=medium] Scan + policy-gate a chat exchange, record it, then run if allowed.","write_action":false,"price_micros":0,"input_schema":null},{"name":"pin_model_digest","description":"[WRITE][risk=medium] Pin a model's expected provenance digest (drift detection).","write_action":false,"price_micros":0,"input_schema":null},{"name":"policy_view","description":"[READ] The current model allow/deny policy + provenance digest pins.","write_action":false,"price_micros":0,"input_schema":null},{"name":"proxy_guidance","description":"[READ] How to run the transparent capture proxy, and what it does NOT guarantee.","write_action":false,"price_micros":0,"input_schema":null},{"name":"pull_model","description":"[WRITE][risk=medium] Pull a model — refused if it violates the deny/allow policy.","write_action":false,"price_micros":0,"input_schema":null},{"name":"remove_model","description":"[WRITE][risk=high] Delete a local model. Destructive — pass dry_run=True to preview.","write_action":true,"price_micros":0,"input_schema":null},{"name":"running_models","description":"[READ] Currently loaded models: VRAM footprint + residency expiry.","write_action":false,"price_micros":0,"input_schema":null},{"name":"scan_prompt","description":"[READ] Pure content scan of a text for secrets / PII / code / jailbreak.","write_action":false,"price_micros":0,"input_schema":null},{"name":"server_status","description":"[READ] Ollama reachability + version.","write_action":false,"price_micros":0,"input_schema":null},{"name":"set_model_allowlist","description":"[WRITE][risk=medium] Replace the model allowlist (glob patterns; empty = allow-all).","write_action":false,"price_micros":0,"input_schema":null},{"name":"set_model_denylist","description":"[WRITE][risk=medium] Replace the model denylist (deny patterns always win).","write_action":false,"price_micros":0,"input_schema":null},{"name":"undo_apply","description":"[WRITE][risk=medium] Apply a recorded undo by dispatching its inverse tool.","write_action":false,"price_micros":0,"input_schema":null},{"name":"undo_list","description":"[READ] List recorded, not-yet-applied undo tokens (most recent first).","write_action":false,"price_micros":0,"input_schema":null},{"name":"unload_model","description":"[WRITE][risk=medium] Evict a model from VRAM (keep_alive:0).","write_action":false,"price_micros":0,"input_schema":null},{"name":"usage_events","description":"[READ] Query the observed-usage log (route-through prompts + their findings).","write_action":false,"price_micros":0,"input_schema":null},{"name":"vram_usage","description":"[READ] Total VRAM used by loaded models; flag over-budget.","write_action":false,"price_micros":0,"input_schema":null}],"scan":{"score":91,"grade":"A","scanned_at":"2026-09-19T19:50:19.004Z","report":{"scannerVersion":"0.1.5","scannedAt":"2026-09-19T19:50:18.984Z","components":{"code":{"score":25,"max":25,"notes":["55 source files scanned"]},"reliability":{"score":-1,"max":20,"notes":["no gateway calls yet and no remote to probe"]},"poisoning":{"score":-1,"max":15,"notes":["tools not inspected (local package is not executed); not counted"]},"auth":{"score":12,"max":15,"notes":["local package, no credentials required"]},"maintenance":{"score":15,"max":15,"notes":["last push 3 days ago"]},"identity":{"score":7,"max":10,"notes":["registry namespace matches repository owner"]}},"findings":[],"inputs":{"packages":[{"registryType":"pypi","identifier":"ai-guardian-aiops","version":"0.11.3","found":true,"weeklyDownloads":583,"license":"MIT","dependencyCount":6,"publishedAt":"2026-09-15T05:45:51.100881Z"}],"repo":{"found":true,"owner":"AIops-tools","repo":"AI-Guardian","archived":false,"pushedAt":"2026-09-16T12:54:16Z","stars":0,"forks":0,"openIssues":0,"ownerType":"Organization","ownerAvatarUrl":"https://avatars.githubusercontent.com/u/295714335?v=4","ownerCreatedAt":"2026-06-22T02:46:57Z","license":"MIT"},"icon":{"url":null,"source":"none"},"presence":{"stars":0,"forks":0,"downloadsWeek":583,"license":"MIT","lastPushAt":"2026-09-16T12:54:16.000Z","score":29}}}},"grade_history":[],"reviews":[]}