{"id":4704,"slug":"jwrede/llmprobe","name":"llmprobe","description":"Probe LLM API endpoints and report health metrics including time to first token, latency, and throughput. Check single models or run full config-based health checks.","category":"development","github":"https://github.com/Jwrede/llmprobe","homepage":"","server_url":"","transport":"stdio","install":null,"tools":[{"name":"probe_all","description":"Probe all configured endpoints from probes.yml. Returns TTFT, latency, throughput, and health status for every model. Accepts an optional config parameter for a custom config path."},{"name":"probe_model","description":"Probe a single model without a config file. Requires provider, model, and api_key_env. Supports optional base_url for OpenAI-compatible endpoints and optional label for display."},{"name":"list_providers","description":"List all providers and models in the config file with their thresholds. Use this to discover available models before probing."},{"name":"get_config","description":"Return the full parsed configuration including defaults, providers, models, and thresholds."}],"env_vars":["OPENAI_API_KEY","ANTHROPIC_API_KEY","AZURE_OPENAI_API_KEY","AWS_ACCESS_KEY_ID","AWS_SECRET_ACCESS_KEY","GROQ_API_KEY","DEEPSEEK_API_KEY","TOGETHER_API_KEY"],"auth_type":"none","official":false,"stars":1,"status":"active","source":"mcpservers.org","created_at":"2026-05-25T11:38:28.668683+00:00","updated_at":"2026-05-28T09:22:54.169715+00:00","tags":[],"path":"llmprobe"}