Traced LLM Proxy is answering right now. Last checked 11 min ago. It exposes 2 tools.
Traced LLM Proxy
Uptime history
7 days of history
7 days agonow
100.0%
Uptime 24h
92 of 92 checks
2
Tools
read from the server
203 ms
Response time
average over 24h
open, no key
Access
streamable-http
Nothing serious here today
Today is the operative word: we check Traced LLM Proxy every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 11 min ago.
run in your terminal
claude mcp add traced-llm-proxy --transport http https://traced-llm-proxy.getvda.ai/mcp~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"traced-llm-proxy": {
"url": "https://traced-llm-proxy.getvda.ai/mcp"
}
}
}~/.codex/config.toml
[mcp_servers.traced-llm-proxy]
url = "https://traced-llm-proxy.getvda.ai/mcp".cursor/mcp.json
{
"mcpServers": {
"traced-llm-proxy": {
"url": "https://traced-llm-proxy.getvda.ai/mcp"
}
}
}.vscode/mcp.json
{
"mcpServers": {
"traced-llm-proxy": {
"url": "https://traced-llm-proxy.getvda.ai/mcp"
}
}
}Available tools 2
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
invoke
invoke
Proxy Gemini (Vertex AI) completions wrapped in OpenTelemetry trace spans; returns the answer plus the trace/span id.
selftest
selftest
FREE, no payment required. Runs this agent's real capability on a fixed canned input and returns the genuine result, an honest assertion grade, and the full trust manifest (signed Agent Card, JWKS, governance/licence chain, safety posture) with a proof link for every claim. Intended for registries, graders and auditors: this is behavioural evidence, not a self-description.
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://traced-llm-proxy.getvda.ai/mcp | streamable-http | answering | 164 ms | 11 min ago |
Alternatives to Traced LLM Proxy
same job, measured the same way
A
Traced LLM MCP Proxy
by getvda
Traced LLM MCP Proxy
A
Traced Multi LLM Proxy
by getvda
Traced Multi-LLM Proxy
A
Authenticated LLM Traced Agent
by getvda
Authenticated LLM Traced Agent
A
LLM Orchestration Traced Agent
by getvda
LLM Orchestration Traced Agent
A
LLM Orchestration Agent D2feb0
by getvda
LangSmith-Traced LLM Orchestration Agent
A
Traced Openai Langchain Agent
by getvda
Traced OpenAI LangChain Agent
A
Traced Claude Format Guard
by getvda
Traced Claude Format Guard
A
Authenticated MCP Traced Agent
by getvda
Authenticated MCP Traced Agent
Traced LLM Proxy — questions
Answers built from our own checks of this server.
What can Traced LLM Proxy do?
It exposes 2 tools, read directly from the server on our last check. Among them: invoke, selftest. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README.
How MCP servers expose tools in the first place →
Is Traced LLM Proxy working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 203 ms. The bar chart above shows every period we have measured.
How do I connect Traced LLM Proxy?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Traced LLM Proxy need an API key?
No. Traced LLM Proxy completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 2 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Traced LLM Proxy?
It answers our handshake in 203 ms on average, which is faster than 67% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.