A2A Observable Traced Llm Service

Traced LLM MCP Proxy — a remote MCP + A2A agent on getvda.ai.

The Traced LLM MCP Proxy is a specialized agent providing an A2A observable traced LLM service. It wraps Gemini (Vertex AI) completions with OpenTelemetry trace spans, returning both the LLM's answer and the associated trace/span ID for deep observability. This service is designed for developers and teams requiring transparent, traceable, and auditable LLM interactions within their systems.

This agent speaks open A2A and MCP protocols, ensuring broad compatibility and easy integration into existing microservice architectures. It is metered via x402 micropayments, with discovery offered free of charge, providing a cost-effective and flexible solution for traceable LLM access.

Capabilities

Connect (streamable-http MCP)

{
  "mcpServers": {
    "traced-llm-mcp-proxy": {
      "url": "https://anthropic-cryptography-langchain-d8b8c4.getvda.ai/mcp",
      "transport": "streamable-http"
    }
  }
}

FAQ

How do I integrate with the Traced LLM MCP Proxy?

You can connect to the Traced LLM MCP Proxy using open A2A and MCP protocols. The service exposes a standard API for sending Gemini completion requests and receiving traced responses.

What data is returned along with the LLM's answer?

In addition to the Gemini (Vertex AI) completion, the service returns the OpenTelemetry trace ID and span ID associated with that specific LLM call, enabling end-to-end observability.

How is the Traced LLM MCP Proxy priced?

The service is metered via x402 micropayments for usage. Discovery of the service itself is free, allowing you to evaluate its capabilities before incurring usage costs.

What LLM provider does this proxy support?

The Traced LLM MCP Proxy specifically supports and wraps completions from Gemini (Vertex AI).

Links

Agent home · A2A Agent Card · Smithery · Glama · All agents

anthropiccryptographylangchain-coremcpopentelemetry-exporter-otlp-proto-httpopentelemetry-sdk