How to Use the Directus MCP in Google ADK

Q: How do I set up the Directus MCP Server with Google ADK?

Install the SDK, then define an McpToolset pointing to your Vinkius HTTP URL. Pass this toolset directly into your LlmAgent tools array. Your Gemini agent will immediately auto-discover all database tools.

Q: How do I limit my Gemini agent to read-only database operations?

Use the toolnames parameter in your McpToolset configuration to expose only getsingleitem and listcollectionitems. This prevents the agent from calling write operations like patchcmsrecord.

Equip your Google ADK agents with direct access to Directus SQL databases using this MCP Server.

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

Map complex schemas using the Google ADK

Enterprise databases often have hundreds of tables that overwhelm standard LLMs. By using `list_schema_collections` and `get_collection_details`, your Gemini-powered agent reads your entire PostgreSQL layout to understand complex relationships. With Gemini's massive context window, the agent holds your entire database map in memory. It uses `list_collection_fields` to inspect columns, matching your CRM data with Google Cloud infrastructure or BigQuery datasets.

Live SQL record management

Let your agent update database records directly from your Python workflows. This MCP Server uses `create_cms_record` to insert new JSON payloads and `patch_cms_record` to update existing rows using specific IDs. This setup is built for high-throughput enterprise environments. If your agent detects duplicate or orphaned records during an audit, it can call `wipe_cms_record` to clean up your database tables automatically.

Media and identity audits

Track files and user accounts across your entire instance. Your agent invokes `list_directus_files` to verify media storage paths and `list_directus_users` to audit active admin accounts. For deeper analysis, the agent uses `get_single_item` to pull specific row UUIDs and `list_collection_items` to query table contents. This keeps your records clean and your media library organized.

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

Install the SDK, then define an `McpToolset` pointing to your Vinkius HTTP URL. Pass this toolset directly into your `LlmAgent` tools array. Your Gemini agent will immediately auto-discover all database tools.

Yes. You can write a script where the agent queries tables using `list_collection_items`, processes the data using Gemini's reasoning, and then writes the structured output to BigQuery using Google Cloud tools.

Vinkius manages the connection security using a single secure endpoint token. You pass this token in your HTTP transport configuration when initializing the toolset in Python, keeping your database credentials hidden from the LLM.

Use the `tool_names` parameter in your `McpToolset` configuration to expose only `get_single_item` and `list_collection_items`. This prevents the agent from calling write operations like `patch_cms_record`.

All database communication runs through ephemeral, zero-trust V8 isolates on Vinkius. Your SQL tables and user records are never cached, and the server only processes the exact rows requested during tool execution.

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