Skip to main content
Anthropic ships Claude on three interfaces — the Claude Code CLI (and VS Code extension), the Claude Desktop app (Cowork), and Claude Web (claude.ai and the mobile apps) — sold under several plans: Enterprise, Team, Pro, and Max. What TrueFoundry can govern depends on both: the interface decides whether the app can be pointed at a gateway at all, and the plan decides how it authenticates and whether Anthropic’s own admin controls are available.

​
What you get at a glance

Full means every model and MCP call passes through the AI Gateway, so you get cost attribution, budgets, rate limits, access control, guardrails, and a full audit trail. Governance only means the model call itself runs in Anthropic’s cloud — the gateway sees the content for guardrails and audit, but there are no tokens to meter. ¹ In third-party inference mode Claude Desktop bills through the model account on the gateway rather than the user’s subscription. See the note at the top of the Desktop page.

​
Two ways Claude authenticates to the gateway

Every Claude integration below uses one of two auth patterns. Knowing which one you’re on explains most of the configuration differences between plans. Both patterns give the gateway full visibility, so cost tracking, guardrails, and audit work the same way on either.

​
Pick your starting point

Quick start

Route Claude Code on one machine through the gateway in five minutes.

Claude Code

CLI and VS Code extension, with per-plan authentication.

Claude Desktop & Cowork

Third-party inference mode, per user or fleet-wide.

Claude Web

Govern claude.ai and the mobile apps with inference hooks or aitori.

Govern MCP traffic

Route every MCP server Claude reaches through the MCP Gateway.

Enforce with MDM

Lock the gateway config on every developer machine.
Billing by plan, which token goes where, and the errors people hit most are answered in the FAQ.

​
Guardrails beyond the model call

Routing model traffic through the gateway governs what Claude sends to the model. Two hook integrations extend that to what Claude does:
  • Anthropic Inference Hooks — Enterprise only. One setting in Anthropic’s admin console sends every prompt from claude.ai, Desktop, Code, and the mobile apps to the gateway for an allow/deny verdict before inference. Nothing to install on devices.
  • Claude Code hooks — any plan. Client-side hooks post prompts and tool calls to the gateway, which can block or rewrite them.

​
Before you start

1

Create a TrueFoundry account

Sign up and follow the Gateway quick start to get your gateway base URL and API key.
2

Add a Claude model account

Connect Anthropic, Bedrock, or Vertex via Anthropic model integration. For subscription passthrough, leave the API key empty.
3

Pick the integration guide for your interface

Use the cards above, or start with the quick start.