About Jwrede/llmprobe
Jwrede/llmprobe is an MCP server in the Blockchain category: synthetic monitoring for LLM inference endpoints. Measure TTFT, latency, throughput, and errors across OpenAI, Anthropic, Google, Azure, Bedrock, and local servers (vLLM, SGLang, Ollama). CLI + MCP server with Prometheus and OpenTelemetry export.
Install
git clone https://github.com/Jwrede/llmprobeThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (4)
get_configReturn the full parsed configuration including defaults, providers, models, and thresholds.
Parameters not published.
list_providersList all providers and models in the config file with their thresholds. Use this to discover available models before probing.
Parameters not published.
probe_allProbe 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.
Parameters not published.
probe_modelProbe 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.
Parameters not published.
Ask AI
Ask AI about Jwrede/llmprobe
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.