How to Use the VectorShift (AI Workflow & RAG Automation) MCP in Google ADK

Q: How do I automate a multi-stage workflow using VectorShift (AI Workflow & RAG Automation) with the Google ADK?

You define the flow first by creating a pipeline via createpipeline. Then, your agent executes it using runpipeline, managing inputs and outputs across all defined steps. The MCP Server handles the complex execution logic for you.

Q: What's the best way to get data contextually from my enterprise documents using VectorShift (AI Workflow & RAG Automation) with the Google ADK?

Use queryknowledgebase. This tool performs semantic search, which means it understands the meaning behind your query and pulls relevant chunks of text. You just need to ensure the data is added first via indexknowledgebase.

Q: If I want to change my chatbot's source documents using VectorShift (AI Workflow & RAG Automation) with the Google ADK, what steps do I take?

You can start by listing existing files with listknowledgebasedocuments to see what you have. To update it, use indexknowledgebase for new data or delete old records using deleteknowledgebasedocuments.

Build enterprise AI agents on Google Cloud using the Google ADK and VectorShift (AI Workflow & RAG Automation).

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect VectorShift (AI Workflow & RAG Automation) MCP to Google ADK

Create your Vinkius account to connect VectorShift (AI Workflow & RAG Automation) 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 VectorShift (AI Workflow & RAG Automation) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Knowledge Bases

Need to connect your agent to corporate documents? The `query_knowledge_base` tool runs semantic search against a knowledge base. This helps your Gemini models find accurate answers from company data. You can populate this system by calling `index_knowledge_base`, which accepts various file types and URLs for ingestion.

Build Chatbots

Setting up a conversational agent is straightforward. You start with `create_chatbot` to initialize the service. For specific context, you can use `upload_chatbot_files` to attach relevant documents directly to the chat session. Once ready, passing a message through `run_chatbot` lets your Google ADK agent interact and respond using the provided knowledge.

Run Complex Workflows

Workflows require coordination. Use `create_pipeline` to map out multi-step processes, ensuring data flows correctly from one stage to the next. This structure is key for reliable enterprise agents. The agent executes these steps by calling `run_pipeline`. If you need to modify data mid-flow, use `run_transformation` to execute custom Python or JavaScript logic.

Setup guide

Set up VectorShift (AI Workflow & RAG Automation) 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 VectorShift (AI Workflow & RAG Automation) 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="VectorShift (AI Workflow & RAG Automation)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to VectorShift (AI Workflow & RAG Automation) 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 VectorShift. 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 VectorShift (AI Workflow & RAG Automation) 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 VectorShift (AI Workflow & RAG Automation) MCP in Google ADK

You define the flow first by creating a pipeline via `create_pipeline`. Then, your agent executes it using `run_pipeline`, managing inputs and outputs across all defined steps. The MCP Server handles the complex execution logic for you.

Use `query_knowledge_base`. This tool performs semantic search, which means it understands the meaning behind your query and pulls relevant chunks of text. You just need to ensure the data is added first via `index_knowledge_base`.

You can start by listing existing files with `list_knowledge_base_documents` to see what you have. To update it, use `index_knowledge_base` for new data or delete old records using `delete_knowledge_base_documents`.

You have controls for running pipelines and chatbots. If a pipeline is stuck, use `pause_pipeline` or `terminate_pipeline`. You can also resume work later by calling `resume_pipeline`.

This server handles file contents and URLs, which are ingested as unstructured text into knowledge bases. The primary data type managed is document content.

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