How to Use the Vertex AI Search MCP in Pydantic AI

Q: How does Vertex AI Search integrate with Pydantic AI?

The pydantic-ai framework treats the MCP Server output as a data object. This means that every piece of information returned by Vertex AI Search is validated against your schema, making the system much more reliable.

Q: Can I list all search engines using Vertex AI Search and Pydantic AI?

Yes, you can call listsearchengines. The resulting list is immediately validated by Pydantic, providing strong type safety for your agent's execution path.

Q: Does the MCP Server validate recommendations with Vertex AI Search and Pydantic AI?

Yes. After calling getrecommendations, Pydantic ensures that the returned data adheres to your required JSON structure, preventing downstream errors from bad API responses.

Guaranteed Data Correctness with Pydantic AI: Validate every Vertex AI Search response at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Vertex AI Search MCP to Pydantic AI

Create your Vinkius account to connect Vertex AI Search to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Vertex AI Search with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get answers grounded in internal documents.

The `get_grounded_answer` tool gives you a natural language answer based on your data. Since the agent receives this output, Pydantic validation ensures that the response structure matches what you expect. If the API returns unexpected content, your agent fails loud with an error—no silent corruption.

Search across all enterprise documents.

When using `search_documents`, Pydantic validation can enforce that the search results are correctly structured. You pass the data store ID and query text, and the tool executes the semantic search. This guarantees that the raw output from the MCP Server adheres to your defined Python schema before your agent uses it.

List all available data stores.

Use `list_data_stores` to confirm which knowledge bases are available. The tool returns a list of all configured data stores, and Pydantic validates this output as a clean list structure. This is useful for an agent that needs to dynamically select the correct source before running any other operation.

Setup guide

Set up Vertex AI Search MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "vertex-ai-search-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Vertex AI Search tools.",
)

result = await agent.run("List recent Vertex AI Search transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Vertex AI Search. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Vertex AI Search now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Vertex AI Search MCP in Pydantic AI

The `pydantic-ai` framework treats the MCP Server output as a data object. This means that every piece of information returned by Vertex AI Search is validated against your schema, making the system much more reliable.

This MCP Server touches document metadata and structured text outputs. The specific data types include configuration details from `get_datastore_details` and the query texts used in searching.

Yes, you can call `list_search_engines`. The resulting list is immediately validated by Pydantic, providing strong type safety for your agent's execution path.

Yes. After calling `get_recommendations`, Pydantic ensures that the returned data adheres to your required JSON structure, preventing downstream errors from bad API responses.

The server handles private document content and metadata. Since Pydantic validates the output fields, you can be certain that only the necessary, structured information leaves the secure search context.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript