Vertex Ai MCP Server

A Model Context Protocol server supporting Vertex AI and Gemini API

Local serverstdioTypeScript

What is the Vertex Ai MCP server?

Vertex Ai MCP server exists for a simple reason — assistants are far more useful when they can act on Vertex Ai directly instead of describing what you should do. A Model Context Protocol server supporting Vertex AI and Gemini API.

What you get

This project implements a Model Context Protocol (MCP) server that provides a comprehensive suite of tools for interacting with Google Cloud's Vertex AI Gemini models, focusing on coding assistance and general query answering.

  • Provides access to Vertex AI Gemini models via numerous MCP tools
  • Supports web search grounding (answer_query_websearch) and direct knowledge answering (answer_query_direct)
  • Configurable model ID, temperature, streaming behavior, max output tokens, and retry settings via environment variables
  • Uses streaming API by default for potentially better responsiveness
  • Includes basic retry logic for transient API errors
  • Minimal safety filters applied (BLOCK_NONE) to reduce potential blocking (use with caution)

What the assistant can call

Once Vertex Ai is connected, these are the calls the assistant has available:

  • code_analysis_with_docs — Analyzes code snippets by comparing them with best practices from official documentation, identifying potential bugs, performance issues, and
  • technical_comparison — Compares multiple technologies, frameworks, or libraries based on specific criteria, providing detailed comparison tables with pros/cons and use
  • architecture_pattern_recommendation — Suggests architecture patterns for specific use cases based on industry best practices, with implementation examples and considerations
  • dependency_vulnerability_scan — Analyzes project dependencies for known security vulnerabilities, providing detailed information and mitigation strategies
  • database_schema_analyzer — Reviews database schemas for normalization, indexing, and performance issues, suggesting improvements based on database-specific best practices
  • security_best_practices_advisor — Provides security recommendations for specific technologies or scenarios, with code examples for implementing secure practices
  • testing_strategy_generator — Creates comprehensive testing strategies for applications or features, suggesting appropriate testing types with coverage goals
  • regulatory_compliance_advisor — Provides guidance on regulatory requirements for specific industries (GDPR, HIPAA, etc.), with implementation approaches for compliance
  • microservice_design_assistant — Helps design microservice architectures for specific domains, with service boundary recommendations and communication patterns
  • documentation_generator — Creates comprehensive documentation for code, APIs, or systems, following industry best practices for technical documentation

Configuration and credentials

You will need 8 environment variables: AI_PROVIDER, GOOGLE_CLOUD_PROJECT, GEMINI_API_KEY, VERTEX_MODEL_ID, GEMINI_MODEL_ID, GOOGLE_CLOUD_LOCATION, AI_TEMPERATURE, AI_USE_STREAMING. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

  • Node.js (v18+) * Bun (npm install -g bun) * Google Cloud Project with Billing enabled. * Vertex AI API enabled in the GCP project. * Google Cloud Authentication configured in your environment (Application Default Credentials via gcloud auth application-default login is recommended, or a Service Account Key).

Setting it up

bun on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Choosing this one

Plenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Vertex Ai's toolset — code_analysis_with_docs, technical_comparison, architecture_pattern_recommendation and 7 more — is a fair guide to whether it matches your workflow. It is maintained by shariqriazz; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 10 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Vertex Ai.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the vertex ai mcp server does with a few real requests.

Available tools

ToolWhat it does
code_analysis_with_docsAnalyzes code snippets by comparing them with best practices from official documentation, identifying potential bugs, performance issues, and security vulnerabilities.
technical_comparisonCompares multiple technologies, frameworks, or libraries based on specific criteria, providing detailed comparison tables with pros/cons and use cases.
architecture_pattern_recommendationSuggests architecture patterns for specific use cases based on industry best practices, with implementation examples and considerations.
dependency_vulnerability_scanAnalyzes project dependencies for known security vulnerabilities, providing detailed information and mitigation strategies.
database_schema_analyzerReviews database schemas for normalization, indexing, and performance issues, suggesting improvements based on database-specific best practices.
security_best_practices_advisorProvides security recommendations for specific technologies or scenarios, with code examples for implementing secure practices.
testing_strategy_generatorCreates comprehensive testing strategies for applications or features, suggesting appropriate testing types with coverage goals.
regulatory_compliance_advisorProvides guidance on regulatory requirements for specific industries (GDPR, HIPAA, etc.), with implementation approaches for compliance.
microservice_design_assistantHelps design microservice architectures for specific domains, with service boundary recommendations and communication patterns.
documentation_generatorCreates comprehensive documentation for code, APIs, or systems, following industry best practices for technical documentation.

How to install the Vertex Ai MCP server

{
  "mcpServers": {
    "vertex-ai": {
      "command": "npx",
      "args": ["-y", "bun"],
      "env": {
        "AI_PROVIDER": "your-value",
        "GOOGLE_CLOUD_PROJECT": "your-value",
        "GEMINI_API_KEY": "your-value",
        "VERTEX_MODEL_ID": "your-value",
        "GEMINI_MODEL_ID": "your-value",
        "GOOGLE_CLOUD_LOCATION": "your-value",
        "AI_TEMPERATURE": "your-value",
        "AI_USE_STREAMING": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • Node.js (v18+) * Bun (npm install -g bun) * Google Cloud Project with Billing enabled. * Vertex AI API enabled in the GCP project. * Google Cloud Authentication configured in your environment (Application Default Credentials via gcloud auth application-default login is recommended, or a Service Account Key).
VariableDescriptionRequired
AI_PROVIDERConfiguration value read at startup.Optional
GOOGLE_CLOUD_PROJECTConfiguration value read at startup.Optional
GEMINI_API_KEYCredential the server authenticates with.Yes
VERTEX_MODEL_IDConfiguration value read at startup.Optional
GEMINI_MODEL_IDConfiguration value read at startup.Optional
GOOGLE_CLOUD_LOCATIONConfiguration value read at startup.Optional
AI_TEMPERATUREConfiguration value read at startup.Optional
AI_USE_STREAMINGConfiguration value read at startup.Optional

Example prompts to try

  • Use Vertex Ai to code analysis with docs.
  • Use Vertex Ai to technical comparison.
  • Use Vertex Ai to architecture pattern recommendation.

Frequently asked questions

It connects Vertex Ai to MCP-compatible AI assistants such as Claude and Cursor, exposing 10 tools (code_analysis_with_docs, technical_comparison, architecture_pattern_recommendation, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Vertex Ai directly.