Traced Multi Llm Proxy
MCP endpoint that routes requests across several LLM providers with tracing
- Platforms
- API
- Runs
- Remotely
- Version
- 1.0.0
- Listing updated
- today
Similar MCP servers
About Traced Multi Llm Proxy
Traced Multi Llm Proxy is an MCP server for ai models and llm tooling. It runs as a hosted remote server, so there is nothing to install locally.
The Traced Multi-LLM Proxy is published as a remote Model Context Protocol server reachable over streamable HTTP at its own domain. Its site describes it as a composition of LLM client libraries, cryptography, LangChain's OpenAI integration, and OpenTelemetry tracing, aimed at combining several model providers behind one endpoint with observability.
The site also advertises an A2A agent card alongside the MCP endpoint, and lists the server on Smithery. The materials available do not document the individual tools the server exposes or detail its pricing, so those points are left unstated here.
It suits developers who want a single MCP endpoint in front of multiple LLM vendors and want request-level tracing of those calls.
Install
Run in a terminal
claude mcp add --transport http traced-multi-llm-proxy https://traced-multi-llm-proxy.getvda.ai/mcpAdd to Settings → Connectors → Add custom connector
https://traced-multi-llm-proxy.getvda.ai/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"traced-multi-llm-proxy": {
"url": "https://traced-multi-llm-proxy.getvda.ai/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"traced-multi-llm-proxy": {
"type": "http",
"url": "https://traced-multi-llm-proxy.getvda.ai/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"traced-multi-llm-proxy": {
"serverUrl": "https://traced-multi-llm-proxy.getvda.ai/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"traced-multi-llm-proxy": {
"type": "http",
"url": "https://traced-multi-llm-proxy.getvda.ai/mcp"
}
}
}Using several servers? Build one config file with the MCP config generator.
What it does
- Remote MCP endpoint
- Exposes an MCP server over streamable HTTP that AI clients can connect to directly.
- Multi-provider LLM routing
- Built on Anthropic and OpenAI-compatible client libraries to reach more than one model vendor.
- Request tracing
- Uses OpenTelemetry components to instrument and observe LLM calls.
- A2A agent card
- Publishes an Agent2Agent card alongside the MCP endpoint for agent-to-agent discovery.
Good for
- Connect an MCP-capable client to several LLM providers through one endpoint
- Trace and monitor LLM calls made by agent workflows
- Expose a multi-model backend to agents over the Agent2Agent protocol
Traced Multi Llm Proxy FAQ
What transport does the MCP server use?
The MCP registry entry lists streamable HTTP, with the endpoint hosted at the product's own domain.
Is it listed in any other directory?
The product's website says it is listed on Smithery.
How do I add Traced Multi Llm Proxy to Claude Code?
Run this command in your terminal: claude mcp add --transport http traced-multi-llm-proxy https://traced-multi-llm-proxy.getvda.ai/mcp
What are the best alternatives to Traced Multi Llm Proxy?
The closest alternatives to Traced Multi Llm Proxy are Traced Llm MCP Proxy, Traced Llm Proxy, Llm Orchestration Agent MCP, Multi Provider Schema Output Agent and Llm Observability Orchestration.
Where this comes from
- Description: written from the project's website and its MCP Registry entry.
- Install steps: from the official MCP Registry entry.