Claude Code can't fix what it can't see. Praxen Inc. shows it your logs, traces and deploys.

Every tool you use, from Claude Code. Praxen Inc. sits between Claude Code and your stack.

Connect your clouds, observability, code and chat once. Claude Code gets three tools: searchTools finds the right one for the question, runTool calls it, and runCode chains several in one go. One sign-in covers every provider, and a tool's schema loads only when Claude Code uses it.

Claude Code

Praxen Inc. MCP

• searchTools find the right tool
• runTool call one
• runCode chain many

AWS Cloudflare Google Cloud Vercel Kubernetes PlanetScale Datadog Sentry Honeycomb Axiom GitHub +32 more

Code mode. Claude Code writes the program, Praxen Inc. runs it.

Calling tools one at a time fills Claude Code's context with raw results: tens of kilobytes of metrics, thousands of log lines, each step waiting on the model. With runCode, Claude Code writes a short program that calls every tool it needs. It runs in Praxen Inc.'s sandbox, and only the answer comes back.

// Which deploy slowed checkout-edge?
const deploys = await tools.deployHistory({ service: "checkout-edge", hours: 24 });
const { points } = await tools.queryMetrics({
  service: "checkout-edge",
  metric: "latency.p99",
  hours: 24,
});

const median = (xs) => xs.sort((a, b) => a - b)[xs.length >> 1] ?? 0;
const p99 = (t, side) =>
  median(points.filter((p) => (side < 0 ? p.t < t : p.t > t)).map((p) => p.v));

// Score every deploy by the p99 shift across its timestamp.
const [worst] = deploys
  .map((d) => ({ ...d, shift: p99(d.at, 1) / p99(d.at, -1) }))
  .sort((a, b) => b.shift - a.shift);

// Pull the error logs right after the suspect deploy.
const errors = await tools.queryLogs({
  service: "checkout-edge",
  level: "error",
  after: worst.at,
  limit: 5,
});

return { deploy: worst.sha, shift: worst.shift, errors };

Ask Claude Code about production. It answers from what's actually running.

Guides for Claude Code

• Guide How to use Claude Code: a practical guide How to use Claude Code: install it, write a CLAUDE.md, pick a permission mode, steer it mid-task, script it with -p and connect it to your tools with MCP.
• Guide Workers Issues: route Cloudflare errors to coding agents Cloudflare's new Workers Issues groups exceptions and 5xx errors and sends them to Claude Code, Cursor, Devin or a webhook. Setup, automations and limits.
• Guide How to use Claude Code to debug production issues Debug production issues with Claude Code: get logs and traces into the session, test hypotheses against evidence, stay read-only and ship a verified fix.
• Guide How to add MCP servers to Cursor How to add MCP servers to Cursor: project and global mcp.json files, remote and local servers, OAuth sign-in, secrets from env vars and tool approvals.
• Guide How to add MCP servers to GitHub Copilot in VS Code How to add MCP servers to GitHub Copilot in VS Code: workspace and user mcp.json, HTTP and stdio servers, MCP: Add Server and confirming tool calls.
• Guide How to use Codex CLI: install, AGENTS.md, MCP and exec How to use Codex CLI: install it, sign in, write an AGENTS.md, set permissions, resume sessions, script it with codex exec and add MCP servers.

Frequently asked questions

Try it with Claude Code. Ask it about production today.