Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.lumiqtrace.com/llms.txt

Use this file to discover all available pages before exploring further.

LumiqTrace provides a hosted MCP (Model Context Protocol) server that lets you query your observability data directly from AI coding tools. Ask questions like “what were the slowest traces in the last hour?” or “run root cause analysis on trace abc123” — without leaving your editor.

​
Endpoint

https://api.lumiqtrace.com/v1/mcp
The server is hosted by LumiqTrace. No local process to run.

​
Authentication

The MCP server uses personal API keys with the lqtp_ prefix. These are separate from project SDK keys (lqt_) and are scoped to your user account.

​
Generate a personal API key

Go to Settings → MCP in the LumiqTrace dashboard. Click Generate key, give it a name, and copy the key — it is shown only once.

​
Client configuration

Open your Claude Desktop configuration file:
  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
Add the lumiqtrace server entry:
{
  "mcpServers": {
    "lumiqtrace": {
      "url": "https://api.lumiqtrace.com/v1/mcp",
      "headers": {
        "Authorization": "Bearer lqtp_YOUR_PERSONAL_API_KEY"
      }
    }
  }
}
Restart Claude Desktop. You should see LumiqTrace tools listed when you start a new conversation.

​
Available tools

The LumiqTrace MCP server exposes 9 tools:
ToolDescription
list_projectsList all projects your account has access to
get_project_overviewSummary of recent activity — event count, error count, avg latency
query_tracesQuery traces with filters: model, status, time range, limit
get_traceFull detail of a single trace by trace ID
get_slow_tracesFind the slowest traces in a given time window
get_metricsAggregated cost, latency, and token usage grouped by model, hour, or day
get_errorsError breakdown grouped by error code, message, and model
natural_language_querySubmit a natural language question about your observability data
root_cause_analysisRun root cause analysis on a failed trace

​
Example prompts

Once connected, you can ask your AI assistant: 
What were the 5 slowest traces in my production project in the last 24 hours?

Run root cause analysis on trace abc123 — why did it fail?

Show me the cost breakdown by model for the last 7 days.

Are there any error spikes in the last hour?

​
Next steps

  • API keys — manage personal and project API keys
  • Traces — explore traces in the dashboard
  • LumiqPilot — AI copilot built into the LumiqTrace dashboard