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 that wraps Gemini (Vertex AI) completions in OpenTelemetry trace spans. It provides the LLM's answer alongside the corresponding trace and span IDs, enabling deep observability and debugging for your AI-powered applications.

This agent is designed for developers and organizations requiring transparent, auditable, and traceable interactions with large language models. It speaks open A2A and MCP protocols, offering seamless integration and is metered via x402 micropayments for discovery-free access.

Capabilities

Connect (streamable-http MCP)

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

FAQ

What is the primary output of this agent?

The agent returns the Gemini (Vertex AI) completion along with the OpenTelemetry trace ID and span ID associated with that completion request.

How do I connect to this A2A observable traced LLM service?

You connect to the agent using the standard A2A and MCP protocols. Specific connection details and API endpoints will be provided upon access.

What is the pricing model for this agent?

Access to this agent is metered via x402 micropayments, ensuring a discovery-free model where you pay only for what you use.

Can I use this agent with other LLMs besides Gemini?

This specific Traced LLM MCP Proxy is designed to proxy Gemini (Vertex AI) completions. It does not natively support other LLM providers.

Links

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

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