How to Use the Directus MCP in Google ADK

Q: How do I configure Google ADK to discover the Directus MCP Server?

Use the McpToolset class with your Vinkius HTTP transport URL. Pass this toolset to your LlmAgent to instantly expose tools like searchitems and getitem to your Gemini models.

Q: Can I limit Google ADK to only read from Directus?

Yes, you can pass a toolnames filter to McpToolset to only expose read-only tools like listitems and getcollection. This prevents the agent from executing writes like createitem.

Q: Can I use this setup to search database content?

Yes. The agent uses searchitems to run full-text search queries across your collections, allowing Gemini to locate specific records quickly.

Q: Where does my Directus schema data go during processing?

Schema metadata read by listfields is processed in memory by your Google ADK agent. Vinkius runs the MCP connector in an isolated sandbox, ensuring your database structure is never exposed or stored.

Connect your enterprise Google ADK agents to Directus tables for long-context database reasoning.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Directus MCP to Google ADK

Create your Vinkius account to connect Directus 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 Directus with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Long-Context Database Reasoning

Google ADK lets Gemini models process massive database contexts by feeding entire tables retrieved via `list_items` directly into the context window. Your agent analyzes thousands of rows at once to find patterns, generate reports, or identify anomalies. Instead of making dozens of small API calls, the agent uses `list_collections` to map your schema and pulls large datasets in a single execution step. This takes full advantage of Gemini's million-token limit.

Enterprise Security with Google ADK and MCP

Secure your database operations by running this MCP Server within your Google Cloud ecosystem. The agent uses `list_roles` and `list_users` to verify user permissions before running sensitive operations like `delete_item` or `update_item`. This setup ensures that your enterprise access controls are respected even when agents operate autonomously. You maintain strict data governance without writing custom security middleware.

Cloud Data Pipeline Synchronization

Sync your headless CMS data directly with BigQuery using automated Google ADK workflows. The agent calls `list_activity` to detect recent changes in Directus and triggers pipeline updates based on modified records. By using `get_collection` and `list_fields` alongside Vertex AI, your agent can automatically update inventory, user profiles, or content catalogs in response to real-time database events.

Setup guide

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

Use the `McpToolset` class with your Vinkius HTTP transport URL. Pass this toolset to your `LlmAgent` to instantly expose tools like `search_items` and `get_item` to your Gemini models.

Yes, you can pass a `tool_names` filter to `McpToolset` to only expose read-only tools like `list_items` and `get_collection`. This prevents the agent from executing writes like `create_item`.

The framework uses Gemini's long-context window to ingest large payloads from `list_files` or `list_items`. It handles large JSON arrays without hitting token limits or losing track of the database schema.

Yes. The agent uses `search_items` to run full-text search queries across your collections, allowing Gemini to locate specific records quickly.

Schema metadata read by `list_fields` is processed in memory by your Google ADK agent. Vinkius runs the MCP connector in an isolated sandbox, ensuring your database structure is never exposed or stored.

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