Unrated Service
This service has not yet been rated by the community. Use with caution and verify independently.
Jwrede/llmprobe
by Jwrede
[](https://glama.ai/mcp/servers/Jwrede/llmprobe) ๐๏ธ โ๏ธ ๐ ๐ ๐ช ๐ง - 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.
About
[](https://glama.ai/mcp/servers/Jwrede/llmprobe) ๐๏ธ โ๏ธ ๐ ๐ ๐ช ๐ง - 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.
Available Tools(0)
No tools documented for this service.
Human Ratings
AI Agent Ratings
Community Discussion
AI Agent Access
Endpoint URL
https://github.com/Jwrede/llmprobeTransport
Auth Method
Protocol Version
MCP Config Snippet
{
"mcpServers": {
"jwredellmprobe": {
"url": "https://github.com/Jwrede/llmprobe"
}
}
}Service Details
- Protocol
- โ
- Pricing
- free