How to Use the Cognee MCP in Google ADK

Q: Can I restrict which Cognee tools my Google ADK agent can access?

Expose only cogneesearch if you want to prevent your agent from writing new data. The ADK allows you to pass an optional list of tool names to filter the exposed tools.

Give your Google ADK enterprise agents a high-fidelity graph memory to ground long-context Gemini models.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cognee MCP to Google ADK

Create your Vinkius account to connect Cognee 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 Cognee with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ground long-context Gemini models using Cognee

`cognee_search` executes natural language queries against your knowledge graph using semantic search. This tool supplies highly relevant context directly to your Google ADK agent, preventing hallucinations in enterprise deployments. Instead of stuffing millions of tokens of raw documents into Gemini, you pull exact entity paths. This targeted approach saves on Vertex AI costs and keeps your agent's reasoning sharp and focused.

Process BigQuery data into structured graphs

`cognee_add_data` ingests unstructured text fields directly from your BigQuery tables. You feed raw database exports straight into the system to start building your graph. Following ingestion, your Google ADK agent runs `cognee_cognify` to extract clean entities and build logical relationships. This transforms standard database rows into an interconnected knowledge base your agent can actually reason about.

Extract entity relationships with this MCP Server

`cognee_get_insights` retrieves structured relationships and hidden connections from your data. Your agent uses these insights to map out complex corporate structures or product dependencies automatically. Setting up this MCP Server requires zero infrastructure management on your end. The Google ADK connects directly via streamable HTTP parameters, exposing the tools to your Vertex AI models instantly.

Setup guide

Set up Cognee 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 Cognee 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="Cognee_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Cognee 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 Cognee. 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 Cognee 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 Cognee MCP in Google ADK

Import McpToolset from the SDK and pass the Vinkius connection URL. Then, simply add this toolset to your LlmAgent constructor to expose the graph tools to Gemini.

Expose only cognee_search if you want to prevent your agent from writing new data. The ADK allows you to pass an optional list of tool names to filter the exposed tools.

Yes, they complement each other perfectly. While Gemini handles massive contexts natively, querying the graph via cognee_get_insights first ensures the model receives highly structured, pre-filtered facts.

The server supports both Stdio and HTTP transports. When running on Vinkius, you connect via a secure, managed HTTP endpoint using a single access token.

All ingested text and extracted graph nodes are processed in isolated memory spaces. Vinkius handles the underlying infrastructure with strict network isolation, ensuring your enterprise database records never leak during the cognify or search phases.

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