For Vertex AI Search MCP Server

A MCP server for Vertex AI Search

Local serverstdioPython

What is the For Vertex AI Search MCP server?

For Vertex AI Search MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. A MCP server for Vertex AI Search.

What you get

This solution uses Gemini with Vertex AI grounding to search documents using your private data. Grounding improves the quality of search results by grounding Gemini's responses in your data stored in Vertex AI Datastore. We can integrate one or multiple Vertex AI data stores to the MCP server. For more details on grounding, refer to Vertex AI Grounding Documentation.

Setting it up

Installation goes through your MCP client rather than a global install: point it at git on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

What the assistant can call

Once For Vertex AI Search is connected, these are the calls the assistant has available:

  • server — server.name: The name of the MCP server
  • model — model.model_name: The name of the Vertex AI model
  • model.project_id — The project ID of the Vertex AI model
  • model.location — The location of the model (e.g. us-central1)
  • model.impersonate_service_account — The service account to impersonate
  • model.generate_content_config — The configuration for the generate content API
  • data_stores — The list of Vertex AI data stores
  • data_stores.project_id — The project ID of the Vertex AI data store
  • data_stores.location — The location of the Vertex AI data store (e.g. us)
  • data_stores.datastore_id — The ID of the Vertex AI data store
  • data_stores.tool_name — The name of the tool
  • data_stores.description — The description of the Vertex AI data store

Configuration and credentials

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 13 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch For Vertex AI Search.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the for vertex ai search mcp server does with a few real requests.

Choosing this one

This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. For Vertex AI Search's toolset — server, model, model.project_id and 10 more — is a fair guide to whether it matches your workflow. It is maintained by ubie-oss; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against For Vertex AI Search's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Available tools

ToolWhat it does
serverserver.name: The name of the MCP server
modelmodel.model_name: The name of the Vertex AI model
model.project_idThe project ID of the Vertex AI model
model.locationThe location of the model (e.g. us-central1)
model.impersonate_service_accountThe service account to impersonate
model.generate_content_configThe configuration for the generate content API
data_storesThe list of Vertex AI data stores
data_stores.project_idThe project ID of the Vertex AI data store
data_stores.locationThe location of the Vertex AI data store (e.g. us)
data_stores.datastore_idThe ID of the Vertex AI data store
data_stores.tool_nameThe name of the tool
data_stores.descriptionThe description of the Vertex AI data store
PrerequisitesThe Prerequisites tool exposed by this server.

How to install the For Vertex AI Search MCP server

{
  "mcpServers": {
    "vertexai-search": {
      "command": "uvx",
      "args": ["git"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

Example prompts to try

  • Use For Vertex AI Search to server.
  • Use For Vertex AI Search to model.
  • Use For Vertex AI Search to model.project id.

Frequently asked questions

It supports one or multiple Vertex AI data stores. The data stores are configured via a YAML config file.