# Traced Llm MCP Proxy

> Traced Llm MCP Proxy is an MCP server for ai models and llm tooling. MCP proxy that adds OpenTelemetry tracing to Anthropic LLM calls for agent builders. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Platforms:** API, Web
- **Website:** https://traced-llm-mcp-proxy.getvda.ai
- **MCP Registry name:** ai.getvda/traced-llm-mcp-proxy
- **Categories:** [AI models and LLM tooling](https://ai-powered.com/categories/ai-and-llm), [developer tools](https://ai-powered.com/categories/developer-tools), [agent tooling](https://ai-powered.com/categories/agent-tooling)
- **Listing updated:** 2026-11-18

## About

Traced LLM MCP Proxy is a remote Model Context Protocol server hosted at getvda.ai. Its page describes it as a composition of the Anthropic client, the MCP library and the OpenTelemetry SDK, covering LLM client access, agent protocol handling and observability.

It is reachable over streamable HTTP at a single /mcp endpoint, so MCP-capable clients can connect without installing a package. The site also links an A2A Agent Card, which means the same service can be addressed through the Agent2Agent protocol as well as MCP.

The page also points to a governance section and a Smithery listing, and places the service in the vendor's wider agent portfolio. It suits developers who want visibility into LLM calls made by their agents. Specific tool names and pricing are not documented on the page.

## Features

- **Remote MCP endpoint:** Connects over streamable HTTP at a hosted /mcp URL with no local install.
- **OpenTelemetry observability:** Built on the OpenTelemetry SDK to support tracing of LLM activity.
- **Anthropic LLM client:** Uses the Anthropic client library as its LLM access layer.
- **A2A Agent Card:** Publishes an Agent Card so it can also be reached via the Agent2Agent protocol.
- **Governance page:** Links to a governance section describing how the agent is managed.

## Good for

- Trace LLM calls made by agents through an MCP proxy
- Add observability to Anthropic-based agent workflows
- Connect an MCP client to a hosted LLM proxy without local setup
- Expose an LLM service to other agents over A2A and MCP

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http traced-llm-mcp-proxy https://traced-llm-mcp-proxy.getvda.ai/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://traced-llm-mcp-proxy.getvda.ai/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "traced-llm-mcp-proxy": {
      "url": "https://traced-llm-mcp-proxy.getvda.ai/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "traced-llm-mcp-proxy": {
      "type": "http",
      "url": "https://traced-llm-mcp-proxy.getvda.ai/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "traced-llm-mcp-proxy": {
      "serverUrl": "https://traced-llm-mcp-proxy.getvda.ai/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "traced-llm-mcp-proxy": {
      "type": "http",
      "url": "https://traced-llm-mcp-proxy.getvda.ai/mcp"
    }
  }
}
```

## FAQ

### How do I connect to it?

Point an MCP client at https://traced-llm-mcp-proxy.getvda.ai/mcp using the streamable HTTP transport.

### Which libraries does it combine?

The page lists anthropic, mcp and opentelemetry-sdk.

### Does it support the A2A protocol?

Yes, the site links an A2A Agent Card alongside the MCP endpoint.

### Is it available on Smithery?

Yes, the page indicates a Smithery listing.

### How do I add Traced Llm MCP Proxy to Claude Code?

Run this command in your terminal: claude mcp add --transport http traced-llm-mcp-proxy https://traced-llm-mcp-proxy.getvda.ai/mcp

### What are the best alternatives to Traced Llm MCP Proxy?

The closest alternatives to Traced Llm MCP Proxy are Traced Llm Proxy, Traced Multi Llm Proxy, Llm Orchestration Agent MCP, Llm Orchestration Traced Agent and Traced Openai Langchain Agent.

## Where this comes from

- Description: written from the project's website and its MCP Registry entry.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [Traced Llm Proxy](https://ai-powered.com/mcp/traced-llm-proxy): Traced Llm Proxy is an MCP server for ai models and llm tooling.
- [Traced Multi Llm Proxy](https://ai-powered.com/mcp/traced-multi-llm-proxy): Traced Multi Llm Proxy is an MCP server for ai models and llm tooling.
- [Llm Orchestration Agent MCP](https://ai-powered.com/mcp/llm-orchestration-agent-mcp): Llm Orchestration Agent MCP is an MCP server for ai models and llm tooling.
- [Llm Orchestration Traced Agent](https://ai-powered.com/mcp/llm-orchestration-traced-agent): Llm Orchestration Traced Agent is an MCP server for ai models and llm tooling.
- [Traced Openai Langchain Agent](https://ai-powered.com/mcp/traced-openai-langchain-agent): Traced Openai Langchain Agent is an MCP server for ai models and llm tooling.
- [Llm Orchestration Agent Cryptography](https://ai-powered.com/mcp/llm-orchestration-agent-cryptography): Llm Orchestration Agent Cryptography is an MCP server for ai models and llm tooling.
- [Structured Output MCP Traced Agent](https://ai-powered.com/mcp/structured-output-mcp-traced-agent): Structured Output MCP Traced Agent is an MCP server for developer tools.
- [Llm Orchestration Agent 2](https://ai-powered.com/mcp/llm-orchestration-agent-2): Llm Orchestration Agent 2 is an MCP server for ai models and llm tooling.

---
Source: https://ai-powered.com/mcp/traced-llm-mcp-proxy
