Argosvix — AI agent observability (87 tools) MCP Server

Argosvix MCP server lets AI agents (Claude Desktop, Cursor, Codex CLI, custom MCP clients) query, manage, and operate their LLM observability data directly from the conversation. Supports both stdio…

Local serverstdioMIT

What is the Argosvix — AI agent observability (87 tools) MCP Server?

Argosvix — AI agent observability (87 tools) is an MCP project maintained in the argosvix/mcp-server repository. The maintainer describes its purpose as “Argosvix MCP server lets AI agents (Claude Desktop, Cursor, Codex CLI, custom MCP clients) query, manage, and operate their LLM observability data directly from the…”. Read the project documentation for the complete scope.

Local setup

The project provides a local client configuration using argosvix-mcp. Follow the repository’s build and installation steps before copying it, and replace example paths with the paths on your own computer.

Configuration values

The example declares ARGOSVIX_API_KEY. Secret-looking values have been replaced with placeholders. Required and optional labels are shown only when the documentation states them.

Source

Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.

Recorded tools

Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.

ToolWhat it does
query_callsRecent LLM call records, filterable by provider / model / time range
get_cost_summaryAggregate cost / calls / tokens by provider or model
list_alertsConfigured alerts + recent trigger status
get_alertDetail of a specific alert + recent trigger history
list_alert_eventsAlert trigger events across the account (notification history)
silence_alertMute a specific alert (= temporary notification stop, default 24h)
unsilence_alertResume notifications for a previously muted alert
create_alertCreate a new alert rule (cost / error rate / latency / anomaly)
acknowledge_alertMark a specific alert event as acknowledged (idempotent, orthogonal to silence)
URIPurpose
cost_reviewCompare 24h / 7d / 30d cost trends and flag anomalies
alert_auditAudit current alert rules and propose improvements
incident_triageInvestigate recent error / latency anomalies (default last 24h)

How to install the Argosvix — AI agent observability (87 tools) MCP Server

{
  "mcpServers": {
    "argosvix": {
      "command": "argosvix-mcp",
      "env": {
        "ARGOSVIX_API_KEY": "YOUR_ARGOSVIX_API_KEY"
      }
    }
  }
}

From the project documentation. Replace placeholders and example paths before connecting.

Configuration

VariableDescriptionRequired
ARGOSVIX_API_KEYDeclared in the maintainer’s client configuration.Check documentation