How to Use the Cognita (RAG Framework) MCP in Google ADK

Q: How do I connect Cognita (RAG Framework) to a Google ADK agent?

Use the McpToolset class in your Python code and point it to the Vinkius HTTP transport URL. Your Google ADK agent will instantly see tools like ragquery and ingestdata as native functions.

Q: Can I restrict tools to read-only for my Gemini agent?

Yes, you can pass a tool name filter to your McpToolset configuration. This MCP Server allows you to prevent the agent from running destructive actions or modifying your active buckets.

Feed Gemini's million-token context window with deep vector chunks from your Google ADK pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cognita (RAG Framework) MCP to Google ADK

Create your Vinkius account to connect Cognita (RAG Framework) 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 Cognita (RAG Framework) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Google ADK native grounding with Cognita

The `rag_query` tool allows your Google ADK agent to pull precise arrays from your rented transformation vectors. This MCP Server keeps your context clean and highly relevant. Your agent can run `search_chunks` to fetch structured presets. This ensures your model grounds its answers in your actual data buckets instead of guessing.

Map BigQuery data to active Cognita buckets

The `list_data_sources` tool extracts structural properties from active buckets to ground your agent. This links your BigQuery pipelines directly to your RAG framework. The agent can then use `list_collections` to identify routing spaces inside the headless Cognita limit. You get a clean bridge between your GCP storage and your live retrieval loop.

Automate ingestion from Google ADK agents

The `ingest_data` tool provisions highly-available JSON payloads directly from your Google ADK pipelines. Your agent can run this on our hosted MCP Server to automatically generate new resource directories on the fly. To keep track of these runs, the agent can call `get_collection` to grab cloud logging traces. This gives you a clear audit trail right inside your Google Cloud logging console.

Setup guide

Set up Cognita (RAG Framework) 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 Cognita (RAG Framework) 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="Cognita (RAG Framework)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Cognita (RAG Framework) 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 Cognita. 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 Cognita (RAG Framework) 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 Cognita (RAG Framework) MCP in Google ADK

Use the `McpToolset` class in your Python code and point it to the Vinkius HTTP transport URL. Your Google ADK agent will instantly see tools like `rag_query` and `ingest_data` as native functions.

Absolutely. Gemini's long context easily digests the large vector arrays returned by `search_chunks` and `rag_query`, allowing for deep reasoning over complex documents.

Vinkius handles the authorization layer with a single endpoint token. Your Google ADK agent simply makes standard HTTP calls to the MCP Server, keeping your GCP credentials secure.

Yes, you can pass a tool name filter to your `McpToolset` configuration. This MCP Server allows you to prevent the agent from running destructive actions or modifying your active buckets.

Your active buckets and vector data are accessed over encrypted TLS channels. The Vinkius sandbox ensures that no data from your RAG queries is cached or stored outside your active session.

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