12 tools that work with Vertex AI: 6 MCP servers, 6 Agent Skills and 0 Claude Code plugins. 6 of the remote servers answered our live check, 0 worked without an API key, and 0 come from an official or verified publisher. Ranked by GitHub stars plus official, live and free-to-try signals.
Most common uses: Multi-agent, orchestration & workflows (6), Models, LLM APIs, routing, serving, training & GPUs (6).
| Tool | Stars | Last update | License | |
|---|---|---|---|---|
| adk-agent-builder Scaffold production-ready AI agents on Google's Agent Development Kit (ADK): ReAct-style single agents, multi-agent orchestration (Sequential/Parallel SkillInstall · skills CLI | 2,919 | MIT | ||
| adk-deployment-specialist Deploy and orchestrate Vertex AI ADK agents using A2A protocol. Manages AgentCard discovery, task submission, Code Execution Sandbox, and Memory Bank. SkillInstall · skills CLI | 2,919 | MIT | ||
| adk-engineer Execute software engineer specializing in creating production-ready ADK agents with best practices, code structure, testing, and deployment automation SkillInstall · skills CLI | 2,919 | MIT | ||
| validator-expert Validate production readiness of Vertex AI Agent Engine deployments across security, monitoring, performance, compliance, and best practices. Generate SkillInstall · skills CLI | 2,919 | MIT | ||
| vertex-agent-builder Build and deploy generative AI agents on Vertex AI: Gemini model selection, RAG with grounded retrieval, function calling, multimodal extraction, eval SkillInstall · skills CLI | 2,919 | MIT | ||
| vertex-engine-inspector Inspect and validate Vertex AI Agent Engine deployments including Code Execution Sandbox, Memory Bank, A2A protocol compliance, and security posture. SkillInstall · skills CLI | 2,919 | MIT | ||
| io.github.mikerawsonnz/authenticated-llm-agent JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion. MCP serverGitHub-verified authorRemote● Live | 1 | MIT | ||
| io.github.mikerawsonnz/authenticated-multi-llm-agent Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion f MCP serverGitHub-verified authorRemote● Live | 1 | MIT | ||
| io.github.mikerawsonnz/llm-observability-orchestration Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith MCP serverGitHub-verified authorRemote● Live | 1 | MIT | ||
| io.github.mikerawsonnz/llm-orchestration-agent Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith MCP serverGitHub-verified authorRemote● Live | 1 | MIT | ||
| io.github.mikerawsonnz/structured-output-agent Turn a prompt + a field schema into validated, typed JSON (Instructor over Gemini 2.5 Flash on Verte MCP serverGitHub-verified authorRemote● Live | 1 | MIT | ||
| io.github.mikerawsonnz/traced-llm-proxy Proxy Gemini (Vertex AI) completions wrapped in OpenTelemetry trace spans; returns the answer plus t MCP serverGitHub-verified authorRemote● Live | 1 | MIT |