Overview

Claude Desktop on third-party (3P) is a deployment mode of Claude Desktop that routes all model inference through a provider you configure: Google Cloud’s Agent Platform, Amazon Bedrock, Microsoft Foundry, any compatible gateway you operate, or the Anthropic API directly. The app runs from a bundled local web application, and conversation history is stored on the user’s device. You get the full Claude Desktop experience (Chat, Cowork, and Code, including file creation, multi-step research, and sub-agent coordination) with inference and billing handled by the provider you choose.

​

Who it’s for

Claude Desktop on 3P is designed for organizations whose security, regulatory, or contractual requirements prevent them from sending data through Anthropic’s first-party products (claude.ai or the Claude API). Typical deployments include:

• Highly regulated enterprises on 3P only: organizations that use third-party inference for regulatory or security reasons
• International enterprises with data residency requirements: organizations that require in-region data residency and cannot send conversation data to the United States

How far a deployment is separated from Anthropic depends on the provider you choose. On Google Cloud’s Agent Platform and Amazon Bedrock, the cloud provider processes conversation data in the region you select. On Microsoft Foundry, Anthropic operates the Claude models, and residency follows the Foundry deployment type. Review Data handling by provider and Data residency and international deployment before choosing a provider. If your organization can use Anthropic’s first-party products directly, standard Claude Desktop with Cowork on a Team or Enterprise plan is simpler to deploy and releases new features more quickly than Claude Desktop on 3P. Choose Claude Desktop on 3P when routing inference through Anthropic’s API is not an option.

​

Architecture

Claude Desktop on 3P keeps the standard feature set and relocates inference to the provider you configure. The desktop app detects 3P mode at launch from the configured inference provider. When a provider and its credentials are present, the sign-in screen offers the option to skip Anthropic authentication and start the app using your inference-provider configuration instead.

​

Security posture

• Conversation content goes only to your configured endpoint. The app sends prompts, responses, files, and tool outputs only to your configured inference endpoint and stores them only on the local machine. What happens to that content at the endpoint depends on the provider, as described under Data handling by provider.
• Sandboxed tool execution. Shell commands run in the hardened Cowork VM; file access is scoped to your allowed folders and web fetches to your egress allowlist.
• Auditable telemetry. Crash reports and product analytics are scrubbed of conversation and user data before being sent to Anthropic, and can be fully disabled via configuration keys. Independently, you can export session activity to your own OpenTelemetry collector. The export is metadata only by default, with prompt and tool content available as an explicit opt-in.
• Centrally managed. Configuration is delivered through your existing MDM (Jamf, Intune, Workspace ONE, Group Policy), a bootstrap server, or the admin console. End users cannot override a configuration that MDM delivers.

For a detailed treatment of the threat model, sandbox boundaries, and data flows, request access to the Claude Cowork Desktop Security Architecture Overview on Anthropic’s Trust Center. For architecture, telemetry, and controls information specific to Claude Desktop on 3P, see the Claude Desktop Security Overview (Third-party platforms) on the Trust Center.

​

Data handling by provider

Once conversation content reaches your inference endpoint, how it is handled depends on the provider you configured. For Google Cloud’s Agent Platform and Amazon Bedrock, data handling is governed by Google Cloud and Amazon Bedrock respectively. Microsoft Foundry offers Claude models in two hosting options, Hosted on Azure and Hosted on Anthropic, and you choose one when you configure the model deployment in Microsoft Foundry. Under both options, Anthropic operates the Claude models and handles conversation data as an independent processor for Microsoft. Your use of Claude through Microsoft Foundry is subject to Anthropic’s data use terms. Deployments hosted on Azure run inference in an Anthropic-operated service on Azure infrastructure, not in your Azure tenant, and prompts and completions remain within Azure. The only data the service sends out of Azure to Anthropic is usage metadata and any content that Anthropic’s safety systems flag. Deployments hosted on Anthropic send prompts and completions to Anthropic’s own infrastructure for inference. See hosting options for Claude in Microsoft Foundry for details. For the Anthropic API, Anthropic processes conversation data under your Anthropic agreement, as described on the Claude API page. For an LLM gateway you operate, data handling depends on the upstream provider your gateway routes each request to.

​

Data residency and international deployment

Google Cloud’s Agent Platform and Amazon Bedrock: Inference requests go directly from the user’s machine to the regional endpoint you configure. Conversation data goes only to that endpoint, to local disk, and optionally to your configured OpenTelemetry collector. Residency is determined by:

1. The cloud region you select for inference
2. The physical location of the user’s device, where conversations are persisted

For multi-region organizations, deploy distinct MDM configuration profiles per geography so each user population points at an in-region endpoint. Google Cloud’s Agent Platform and Amazon Bedrock each offer Claude models in the EU, UK, and Asia/Pacific regions; consult your provider’s model-availability documentation for the current list. Microsoft Foundry: Residency is set by the hosting option and deployment type you select when you deploy the model in Microsoft Foundry. Deployments hosted on Azure offer two deployment types: Global Standard, which may run inference in any available region, and US Data Zone Standard, which keeps inference within the United States. Deployments hosted on Anthropic offer Global Standard only. As with the other providers, conversation history is stored on the user’s device. See hosting options for Claude in Microsoft Foundry for details.

​

Public sector and highly regulated environments

This section applies when using Google Cloud’s Agent Platform or Amazon Bedrock. Because inference runs in your cloud tenant, Claude Desktop on 3P operates inside whatever compliance boundary your provider and region give you. The desktop application itself contacts Anthropic-operated hosts only to download the VM workspace bundle and Claude CLI binary (always required), and for crash reporting, product analytics, non-essential services (connector favicons, artifact previews, and MCP Apps widgets), and auto-updates. Each of the latter four can be disabled independently via managed configuration. With Anthropic-bound telemetry, non-essential services, and updates all disabled, the only remaining Anthropic-operated egress is downloads.claude.ai for the VM bundle at session start. An app managed from the Enterprise Admin Console still contacts api.anthropic.com at launch and at each configuration re-check, and claude.ai at sign-in. If Code sessions can use Web Fetch, also set skipWebFetchPreflight to true (or add WebFetch to disabledBuiltinTools), because Claude Code in Code sessions otherwise checks each fetched domain with api.anthropic.com. Beyond that, the compliance posture of your deployment is determined by your inference provider. See Telemetry and egress for the full set of network paths and how to lock them down.

​

HIPAA

For Google Cloud’s Agent Platform and Amazon Bedrock, Claude Desktop on 3P does not send user data, prompts, or completions to Anthropic, so Anthropic does not interact with PHI a user may upload to Claude Desktop on 3P. Claude Desktop on 3P transmits that data only to your cloud service provider and to any remote MCP servers you choose to configure. For a HIPAA-compliant solution, ensure you have a BAA in place with your cloud service provider and review any MCP servers for HIPAA compliance before connecting them to Claude Desktop on 3P. You don’t need to disable telemetry to meet HIPAA requirements, because Anthropic’s telemetry carries only redacted crash reports and aggregated usage metrics, never user data, prompts, or completions. For Microsoft Foundry, HIPAA readiness is not available. Anthropic operates the Claude models in Microsoft Foundry and processes conversation data, as described under Data handling by provider, and Anthropic’s HIPAA readiness arrangement (a signed BAA plus safeguards for processing PHI through the Claude API) does not cover Microsoft Foundry. See What HIPAA readiness does not cover in the Claude API documentation. If your deployment must handle PHI, configure Google Cloud’s Agent Platform or Amazon Bedrock as the inference provider and put a BAA in place with that provider.

​

Next steps