How to Use the Vectara MCP in Google ADK

Q: What is the best way to search data with Vectara and Google ADK?

You use performsemanticsearch. You pass the corpus keys and query text. The MCP Server runs a semantic search across your designated corpora, giving you accurate results.

Q: Can I check what data is available with Vectara and Google ADK?

You can list all searchable datasets using listcorpora. If you need to know more about a specific dataset's setup, call getcorpusdetails.

Q: Does the MCP Server support deleting data?

Yes. The tool deletecorpusdocument lets you permanently remove documents from a corpus. Just remember, this process is irreversible.

Q: How does the MCP Server manage chat history with Vectara and Google ADK?

You can look at past interactions by calling listchatsessions. This helps your agent keep track of previous RAG sessions without needing external state management.

Build enterprise agents on Google Cloud: Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Vectara MCP to Google ADK

Create your Vinkius account to connect Vectara to Google ADK 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 Vectara with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute grounded chats with RAG

The agent starts by calling `execute_rag_chat` when it needs to chat with specific knowledge bases. This gives a summarized AI response that includes citations, so you know where the answer came from. It’s great for complex reasoning because it can hold 1M+ tokens and ground its answers using data sources managed by this MCP Server.

Searching across multiple corpora

To find specific info, the agent runs `perform_semantic_search`. You just provide a list of corpus keys and your search query. It handles running that search across many datasets. This is better than simple keyword matching; it truly understands the context behind your search terms.

Monitoring data assets

You manage everything through listing tools. Use `list_corpora` to see all available search indexes in the account, or use `list_corpus_documents` when you want a full inventory of one specific corpus. For setup details on any dataset, run `get_corpus_details`. It pulls all the necessary metadata.

Setup guide

Set up Vectara MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Vectara tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Vectara_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Vectara tools via MCP.",
    tools=mcp_tools,
)

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 Vectara. 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 Vectara 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 Vectara MCP in Google ADK

The MCP Server works with corpus documents. Since you are building enterprise agents on Google Cloud, these actions integrate into your existing secure infrastructure.

You use `perform_semantic_search`. You pass the corpus keys and query text. The MCP Server runs a semantic search across your designated corpora, giving you accurate results.

You can list all searchable datasets using `list_corpora`. If you need to know more about a specific dataset's setup, call `get_corpus_details`.

Yes. The tool `delete_corpus_document` lets you permanently remove documents from a corpus. Just remember, this process is irreversible.

You can look at past interactions by calling `list_chat_sessions`. This helps your agent keep track of previous RAG sessions without needing external state management.

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