Operate from your AI agent (87 MCP tools)

Drive Argosvix in plain chat from Claude Desktop or Cursor. Ask "what was p95 latency last week?" and the LLM calls a tool to answer.

Demo: Sample conversation in Claude Desktop

Is Claude getting slow lately? How does it compare to the others?
get_percentiles(metric=latency, p=95, since=7d, groupBy=model)
gpt-5: 1.8s, claude-sonnet-4-6: 1.2s, gemini-2.5-pro: 0.9s. Claude is the fastest.
Alert me on Slack when Claude fails over 8%.
create_alert(name=Claude error rate, condition=model=claude-*, error_rate(15m) > 8%, channel=slack)
Alert "Claude error rate" created. Slack will be notified if a 15-minute window exceeds 8%.

87 MCP tools

From reads to create / update / delete. One of the largest operational tool sets in the space.

Works with major agents

Claude Desktop / Cursor / Codex CLI / Anthropic API / OpenAI Tool. Both stdio and HTTP transport.

Operations are audited

From alert and prompt changes to bulk deletes, write operations are recorded in the audit log with the API key or user that made them.