MCP Observatory
50s ago Tracked 52,799 Last 50s ago 24h 2,818
github Python re-analysis due

AIops-tools/Inference-AIops

github

Governed GPU inference ops (vLLM + Ray Serve): latency RCA, scaling, drain, 30 MCP tools (preview)

maintainer
AIops-tools
license
MIT
first seen
2026-07-12
last seen
2026-09-02
releases · 30d
1
short id

Drift inferred · capture-to-capture

No drift recorded — single capability capture; advisories appear once its surface changes.

capabilities 39 tools
transport stdio · http verified reported listed in the official MCP registry counts 39 tools · 0 res · 0 prompts permission surface via code analysis

tools

  • autoscale_config_get
  • autoscale_config_update
  • cost_per_token
  • deployment_redeploy
  • deployment_status
  • diagnose_engine_latency
  • diagnose_latency_spike
  • diagnose_low_utilization
  • drain_replica
  • engine_health
  • engine_inventory
  • engine_queue_depth
  • engine_request_metrics
  • gpu_utilization
  • kv_cache_stats
  • lora_load
  • lora_unload
  • model_deploy
  • model_info
  • model_is_sleeping
  • model_list
  • model_sleep
  • model_undeploy
  • model_wake
  • queue_depth
  • ray_cluster_resources
  • ray_dashboard_status
  • ray_job_cancel
  • ray_job_list
  • replica_list
  • replica_restart
  • request_metrics
  • routing_policy_update
  • scale_replicas_down
  • scale_replicas_up
  • scale_to_zero
  • serve_deployment_list
  • undo_apply
  • undo_list
skills & danger signals github-tarball
prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed commit 8130778 · analyzer v33 · 2w ago

skills & prompt files 1

code evidence vv0.8.0 · github-tarball
evidence-backed findings quoted directly from the published source artifact — not inferred

code files: 75

filesystem 12

  • fs AIops-tools-Inference-AIops-8130778/inference_aiops/cli/_common.py :7 from pathlib import Path
  • fs AIops-tools-Inference-AIops-8130778/inference_aiops/config.py :23 from pathlib import Path
  • fs AIops-tools-Inference-AIops-8130778/inference_aiops/governance/audit.py :16 from pathlib import Path
  • fs AIops-tools-Inference-AIops-8130778/inference_aiops/governance/paths.py :11 from pathlib import Path
  • fs AIops-tools-Inference-AIops-8130778/inference_aiops/governance/patterns.py :34 from pathlib import Path
  • fs AIops-tools-Inference-AIops-8130778/inference_aiops/governance/undo.py :34 from pathlib import Path
  • fs AIops-tools-Inference-AIops-8130778/inference_aiops/secretstore.py :36 from pathlib import Path
  • fs AIops-tools-Inference-AIops-8130778/mcp_server/_shared.py :19 from pathlib import Path
  • fs (weak) AIops-tools-Inference-AIops-8130778/tests/test_cli_governed_exit.py :23 import pathlib
  • fs (weak) AIops-tools-Inference-AIops-8130778/tests/test_gov_patterns.py :384 import shutil
  • fs (weak) AIops-tools-Inference-AIops-8130778/tests/test_models.py :9 import pathlib
  • fs (weak) AIops-tools-Inference-AIops-8130778/tests/test_smoke.py :67 from pathlib import Path

shell / exec 1

  • shell (weak) AIops-tools-Inference-AIops-8130778/tests/test_undo_executor.py :201 import subprocess

network 4

  • net AIops-tools-Inference-AIops-8130778/inference_aiops/connection.py :26 import httpx
  • net AIops-tools-Inference-AIops-8130778/inference_aiops/ops/_util.py :16 from urllib.parse import quote
  • net AIops-tools-Inference-AIops-8130778/mcp_server/_shared.py :22 import httpx
  • net (weak) AIops-tools-Inference-AIops-8130778/tests/test_connection_prometheus.py :12 import httpx

secrets 5

  • secrets AIops-tools-Inference-AIops-8130778/inference_aiops/cli/init.py :12 import getpass
  • secrets AIops-tools-Inference-AIops-8130778/inference_aiops/cli/secret.py :10 import getpass
  • secrets AIops-tools-Inference-AIops-8130778/inference_aiops/governance/audit.py :9 import getpass
  • secrets AIops-tools-Inference-AIops-8130778/inference_aiops/secretstore.py :29 import getpass
  • secrets (weak) AIops-tools-Inference-AIops-8130778/tests/test_gov_audit.py :240 import getpass

database 7

  • db AIops-tools-Inference-AIops-8130778/inference_aiops/governance/audit.py :13 import sqlite3
  • db AIops-tools-Inference-AIops-8130778/inference_aiops/governance/undo.py :30 import sqlite3
  • db (weak) AIops-tools-Inference-AIops-8130778/tests/test_cli_writes.py :12 import sqlite3
  • db (weak) AIops-tools-Inference-AIops-8130778/tests/test_gov_audit.py :14 import sqlite3
  • db (weak) AIops-tools-Inference-AIops-8130778/tests/test_gov_decorators.py :22 import sqlite3
  • db (weak) AIops-tools-Inference-AIops-8130778/tests/test_governance_persistence.py :13 import sqlite3
  • db (weak) AIops-tools-Inference-AIops-8130778/tests/test_undo_executor.py :12 import sqlite3

tool registrations 39

  • cost_per_token AIops-tools-Inference-AIops-8130778/mcp_server/tools/cost.py :10
  • model_deploy AIops-tools-Inference-AIops-8130778/mcp_server/tools/deploy.py :29
  • model_undeploy AIops-tools-Inference-AIops-8130778/mcp_server/tools/deploy.py :49
  • deployment_redeploy AIops-tools-Inference-AIops-8130778/mcp_server/tools/deploy.py :70
  • routing_policy_update AIops-tools-Inference-AIops-8130778/mcp_server/tools/deploy.py :94
  • engine_health AIops-tools-Inference-AIops-8130778/mcp_server/tools/engine.py :17
  • engine_inventory AIops-tools-Inference-AIops-8130778/mcp_server/tools/engine.py :29
  • engine_request_metrics AIops-tools-Inference-AIops-8130778/mcp_server/tools/engine.py :44
  • engine_queue_depth AIops-tools-Inference-AIops-8130778/mcp_server/tools/engine.py :56
  • diagnose_engine_latency AIops-tools-Inference-AIops-8130778/mcp_server/tools/engine.py :68
  • request_metrics AIops-tools-Inference-AIops-8130778/mcp_server/tools/metrics.py :10
  • queue_depth AIops-tools-Inference-AIops-8130778/mcp_server/tools/metrics.py :22
  • kv_cache_stats AIops-tools-Inference-AIops-8130778/mcp_server/tools/metrics.py :34
  • diagnose_latency_spike AIops-tools-Inference-AIops-8130778/mcp_server/tools/metrics.py :46
  • diagnose_low_utilization AIops-tools-Inference-AIops-8130778/mcp_server/tools/metrics.py :61
  • model_list AIops-tools-Inference-AIops-8130778/mcp_server/tools/models.py :46
  • model_info AIops-tools-Inference-AIops-8130778/mcp_server/tools/models.py :58
  • model_is_sleeping AIops-tools-Inference-AIops-8130778/mcp_server/tools/models.py :71
  • lora_load AIops-tools-Inference-AIops-8130778/mcp_server/tools/models.py :92
  • lora_unload AIops-tools-Inference-AIops-8130778/mcp_server/tools/models.py :106
  • model_sleep AIops-tools-Inference-AIops-8130778/mcp_server/tools/models.py :127
  • model_wake AIops-tools-Inference-AIops-8130778/mcp_server/tools/models.py :154
  • ray_cluster_resources AIops-tools-Inference-AIops-8130778/mcp_server/tools/ray_cluster.py :16
  • ray_dashboard_status AIops-tools-Inference-AIops-8130778/mcp_server/tools/ray_cluster.py :28
  • ray_job_list AIops-tools-Inference-AIops-8130778/mcp_server/tools/ray_cluster.py :40
  • gpu_utilization AIops-tools-Inference-AIops-8130778/mcp_server/tools/ray_cluster.py :57
  • ray_job_cancel AIops-tools-Inference-AIops-8130778/mcp_server/tools/ray_cluster.py :72
  • replica_restart AIops-tools-Inference-AIops-8130778/mcp_server/tools/ray_cluster.py :85
  • serve_deployment_list AIops-tools-Inference-AIops-8130778/mcp_server/tools/serve.py :67
  • deployment_status AIops-tools-Inference-AIops-8130778/mcp_server/tools/serve.py :79
  • replica_list AIops-tools-Inference-AIops-8130778/mcp_server/tools/serve.py :93
  • autoscale_config_get AIops-tools-Inference-AIops-8130778/mcp_server/tools/serve.py :107
  • scale_replicas_up AIops-tools-Inference-AIops-8130778/mcp_server/tools/serve.py :124
  • scale_replicas_down AIops-tools-Inference-AIops-8130778/mcp_server/tools/serve.py :151
  • scale_to_zero AIops-tools-Inference-AIops-8130778/mcp_server/tools/serve.py :176
  • autoscale_config_update AIops-tools-Inference-AIops-8130778/mcp_server/tools/serve.py :200
  • drain_replica AIops-tools-Inference-AIops-8130778/mcp_server/tools/serve.py :224
  • undo_list AIops-tools-Inference-AIops-8130778/mcp_server/tools/undo.py :43
  • undo_apply AIops-tools-Inference-AIops-8130778/mcp_server/tools/undo.py :115

declared dependencies 6

  • mcp@>=2.0,<3.0
  • httpx@>=0.27,<1.0
  • typer@>=0.12,<1.0
  • rich@>=13.0,<16.0
  • pyyaml@>=6.0,<7.0
  • cryptography@>=42.0