Vertex AI Claude Code Platform Agent
Community reusable agent prompt for operating Claude Code on Google Vertex AI using official setup docs: GCP projects, service accounts, regions, VPC-SC constraints, billing alerts, and Vertex-specific Claude Code troubleshooting steps.
Open the source and read safety notes before installing.
Safety notes
- Service account keys in repositories are high risk; prefer workload identity federation.
- Vertex endpoints and regions must match data residency commitments.
- Shared service accounts across teams complicate audit—prefer scoped identities.
- GCP org policy changes require admin approval; this agent advises, not applies, policies.
Privacy notes
- Cloud Logging may capture request metadata; configure exclusions for sensitive projects.
- Customer data handling follows Google Cloud and Anthropic terms for Vertex Claude models.
- Support cases should avoid attaching application default credential JSON files.
Prerequisites
- Google Cloud project with Vertex AI API enabled and Claude models available in region.
- Service account or user credentials configured for Claude Code Vertex mode.
- Organization policies for VPC Service Controls or restricted regions if applicable.
- Billing account linkage and budget alerts for generative usage.
Schema details
- Install type
- copy
- Troubleshooting
- No
- Scope
- Source repo
Full copyable content
## Content
Vertex AI Claude Code Platform Agent is a community-authored reusable prompt for teams
connecting Claude Code to Google Vertex AI. It applies official Claude Code on Google
Vertex AI and network-config documentation—not an official Anthropic support agent.
## Scope Note
This prompt operationalizes documented Vertex AI configuration and troubleshooting steps
from code.claude.com. It does not replace Google Cloud support or Anthropic enterprise onboarding.
## Agent Prompt
You are a Vertex AI platform specialist for Claude Code. Help teams configure and debug
Vertex-backed Claude Code using only official Anthropic and Google Cloud documentation references.
Workflow:
1. **Mode confirmation.** Verify Claude Code uses Vertex AI rather than the direct Anthropic API per setup docs.
2. **Project setup.** Check APIs enabled, billing linked, and Claude model availability in the chosen region.
3. **Identity.** Review service accounts, ADC paths, and workforce federation; reject leaked JSON keys in repos.
4. **Networking.** Apply network-config guidance for proxies, Private Google Access, and VPC-SC constraints.
5. **Quotas and billing.** Interpret quota exceeded and billing disabled errors; recommend budgets and limit requests.
6. **Enterprise policy.** Align managed Claude Code settings, logging, and zero-data-retention requirements with Vertex usage.
7. **Runbook.** Provide gcloud verification steps and GCP admin escalation templates with evidence.
Output contract:
- Configuration matrix: project, region, model, principal type.
- Error diagnosis with IAM, quota, or network causes.
- Developer vs GCP admin remediation steps.
- Compliance notes on logging and residency.
## Features
- Maps Vertex setup docs to repeatable troubleshooting workflows.
- Separates developer fixes from IAM or quota admin actions.
- Incorporates VPC-SC and enterprise network-config requirements.
- Produces admin-ready escalation templates.
## Use Cases
- Enable Claude Code for GCP-native engineering teams.
- Debug PERMISSION_DENIED on Vertex Claude calls from CI runners.
- Align Vertex regions with EU data residency programs.
- Document standard service account patterns for Claude Code fleets.
## Source Notes
Verified against Claude Code Google Vertex AI and network-config documentation on
**2026-06-16**:
- Official docs describe configuring Claude Code to call Claude models through Vertex AI
with Google Cloud credentials rather than Anthropic API keys.
- Setup covers project configuration, regional model availability, and authentication
patterns appropriate to enterprise GCP environments.
- Network-config documentation addresses corporate proxies and TLS requirements that
affect Vertex endpoint reachability from developer machines and CI.
## Duplicate Check
Checked content/guides and content/agents for Vertex Claude Code coverage.
claude-code-on-google-vertex-ai-setup is a one-time setup guide. No agents entry provides
ongoing Vertex platform troubleshooting with IAM, quota, and network-config runbooks.
## Editorial Disclosure
Submitted as an independent community agent entry by kiannidev, based on public Claude
Code Google Vertex AI documentation and the public anthropics/claude-code repository.
No paid placement, referral, or affiliate relationship.
## Sources
- Claude Code on Google Vertex AI - https://code.claude.com/docs/en/google-vertex-ai
- Claude Code network config - https://code.claude.com/docs/en/network-config
- Claude Code repository - https://github.com/anthropics/claude-codeAbout this resource
Content
Vertex AI Claude Code Platform Agent is a community-authored reusable prompt for teams connecting Claude Code to Google Vertex AI. It applies official Claude Code on Google Vertex AI and network-config documentation—not an official Anthropic support agent.
Scope Note
This prompt operationalizes documented Vertex AI configuration and troubleshooting steps from code.claude.com. It does not replace Google Cloud support or Anthropic enterprise onboarding.
Agent Prompt
You are a Vertex AI platform specialist for Claude Code. Help teams configure and debug Vertex-backed Claude Code using only official Anthropic and Google Cloud documentation references.
Workflow:
- Mode confirmation. Verify Claude Code uses Vertex AI rather than the direct Anthropic API per setup docs.
- Project setup. Check APIs enabled, billing linked, and Claude model availability in the chosen region.
- Identity. Review service accounts, ADC paths, and workforce federation; reject leaked JSON keys in repos.
- Networking. Apply network-config guidance for proxies, Private Google Access, and VPC-SC constraints.
- Quotas and billing. Interpret quota exceeded and billing disabled errors; recommend budgets and limit requests.
- Enterprise policy. Align managed Claude Code settings, logging, and zero-data-retention requirements with Vertex usage.
- Runbook. Provide gcloud verification steps and GCP admin escalation templates with evidence.
Output contract:
- Configuration matrix: project, region, model, principal type.
- Error diagnosis with IAM, quota, or network causes.
- Developer vs GCP admin remediation steps.
- Compliance notes on logging and residency.
Features
- Maps Vertex setup docs to repeatable troubleshooting workflows.
- Separates developer fixes from IAM or quota admin actions.
- Incorporates VPC-SC and enterprise network-config requirements.
- Produces admin-ready escalation templates.
Use Cases
- Enable Claude Code for GCP-native engineering teams.
- Debug PERMISSION_DENIED on Vertex Claude calls from CI runners.
- Align Vertex regions with EU data residency programs.
- Document standard service account patterns for Claude Code fleets.
Source Notes
Verified against Claude Code Google Vertex AI and network-config documentation on 2026-06-16:
- Official docs describe configuring Claude Code to call Claude models through Vertex AI with Google Cloud credentials rather than Anthropic API keys.
- Setup covers project configuration, regional model availability, and authentication patterns appropriate to enterprise GCP environments.
- Network-config documentation addresses corporate proxies and TLS requirements that affect Vertex endpoint reachability from developer machines and CI.
Duplicate Check
Checked content/guides and content/agents for Vertex Claude Code coverage. claude-code-on-google-vertex-ai-setup is a one-time setup guide. No agents entry provides ongoing Vertex platform troubleshooting with IAM, quota, and network-config runbooks.
Editorial Disclosure
Submitted as an independent community agent entry by kiannidev, based on public Claude Code Google Vertex AI documentation and the public anthropics/claude-code repository. No paid placement, referral, or affiliate relationship.
Sources
- Claude Code on Google Vertex AI - https://code.claude.com/docs/en/google-vertex-ai
- Claude Code network config - https://code.claude.com/docs/en/network-config
- Claude Code repository - https://github.com/anthropics/claude-code
Source citations
Add this badge to your README
Show that Vertex AI Claude Code Platform Agent is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/agents/vertex-ai-claude-code-platform-agent)How it compares
Vertex AI Claude Code Platform Agent side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
| Field | Vertex AI Claude Code Platform Agent Community reusable agent prompt for operating Claude Code on Google Vertex AI using official setup docs: GCP projects, service accounts, regions, VPC-SC constraints, billing alerts, and Vertex-specific Claude Code troubleshooting steps. Open dossier | Bedrock Claude Code Platform Agent Community reusable agent prompt for operating Claude Code on Amazon Bedrock using official setup docs: IAM credential chains, regional model IDs, inference profiles, enterprise network config, quota errors, and Bedrock-specific troubleshooting steps. Open dossier | Microsoft Foundry Claude Code Agent Community reusable agent prompt for operating Claude Code on Microsoft Foundry using official setup docs: Azure subscriptions, Entra ID auth, deployment names, enterprise network config, and Foundry-specific Claude Code troubleshooting steps. Open dossier | Enterprise Network Proxy Debugging Agent Community reusable agent prompt for debugging Claude Code behind corporate HTTP proxies and mTLS using official network-config docs: HTTP_PROXY variables, certificate trust, downloads reachability, and remote MCP URL failures. Open dossier |
|---|---|---|---|---|
| Trust | ||||
| Install risk | Review first | Review first | Review first | Review first |
| Notes | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ |
| Category | agents | agents | agents | agents |
| Source | source-backed | source-backed | source-backed | source-backed |
| Author | kiannidev | kiannidev | kiannidev | kiannidev |
| Added | 2026-06-16 | 2026-06-16 | 2026-06-16 | 2026-06-16 |
| Platforms | Claude Code | Claude Code | Claude Code | Claude Code |
| Source repo | — | — | — | — |
| Safety notes | ✓Service account keys in repositories are high risk; prefer workload identity federation. Vertex endpoints and regions must match data residency commitments. Shared service accounts across teams complicate audit—prefer scoped identities. GCP org policy changes require admin approval; this agent advises, not applies, policies. | ✓Long-lived access keys in repositories are forbidden; prefer IAM roles and OIDC for CI. Bedrock model allowlists should match security-approved model IDs only. Cross-region failover can violate data residency—confirm before switching regions. IAM policy changes require cloud admin approval; this agent advises, not applies, policies. | ✓Client secrets and connection strings must not be committed to repositories. Deployment names and API versions must match Foundry-supported Claude models only. Cross-subscription resources can break policy—keep Foundry resources in approved subscriptions. Azure RBAC changes require admin approval; this agent advises, not applies, policies. | ✓Do not paste proxy credentials or client private keys into shared chat logs. Disabling TLS verification globally is not an acceptable production fix. Split-tunnel VPN changes affect MCP SaaS endpoints—coordinate with security teams. Debugging commands should use read-only curl or openssl checks before changing production laptops. |
| Privacy notes | ✓Cloud Logging may capture request metadata; configure exclusions for sensitive projects. Customer data handling follows Google Cloud and Anthropic terms for Vertex Claude models. Support cases should avoid attaching application default credential JSON files. | ✓Bedrock invocation logs and CloudTrail events may contain prompt metadata—configure retention. Customer content handling follows AWS Bedrock and Anthropic agreements for your account type. Support bundles should redact account IDs and role ARNs when shared externally. | ✓Azure Monitor and Foundry logs may store request metadata; configure retention accordingly. Customer content handling follows Microsoft and Anthropic agreements for Foundry Claude. Support tickets should redact tenant IDs and subscription names when posted publicly. | ✓Proxy logs may capture Anthropic API paths and internal MCP hostnames. Packet captures for debugging must follow company retention and access policies. Support tickets should redact employee emails and internal gateway URLs when possible. |
| Prerequisites |
|
|
|
|
| Install | — | — | — | — |
| Config | — | — | — | — |
| Citations | ||||
| Claim | Unclaimed | Unclaimed | Unclaimed | Unclaimed |
Signals
Loading live community signals…
A short, calm digest of reviewed Claude resources. Unsubscribe any time.