How to Use the DatoCMS MCP in Google ADK

Q: How do I configure Google ADK to use the DatoCMS MCP Server?

Initialize an McpToolset with your Vinkius HTTP endpoint URL. Pass this toolset to your LlmAgent constructor. The tools become immediately available to your Gemini models.

Q: Can I restrict which DatoCMS tools my Google ADK agent sees?

You pass a toolnames filter when setting up the toolset. This limits the agent to specific operations like executegraphqlcda or listglobalmodels. It prevents the model from accidentally triggering destructive actions.

Q: How does Google ADK handle complex DatoCMS content models?

The agent uses listglobalmodels to read the structured rules. Gemini's massive context window holds the entire schema definition in memory. This allows the model to generate perfectly formatted payloads for write operations.

Connect your Gemini agents to DatoCMS using Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DatoCMS MCP to Google ADK

Create your Vinkius account to connect DatoCMS 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 DatoCMS with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Direct access via the DatoCMS MCP Server.

The DatoCMS MCP Server feeds headless content directly into your Google ADK pipelines. Your Gemini models use `execute_graphql_cda` to pull deep routing spaces from the GraphQL tree. They process massive JSON responses using their 1M+ token context windows. Cross-referencing CMS data with enterprise infrastructure becomes trivial. An agent extracts active node details via `get_single_record` and immediately joins that data with BigQuery tables. You stop writing glue code and let the agent handle the mapping.

Bulk record management and auditing.

Bulk record management relies on clear API interactions. The `list_cma_records` tool grabs explicit JSON:API arrays from the cloud log. Your agent parses these arrays to audit content state across the entire project. Updates happen through `patch_cms_record` and `create_cms_record`. You define the mutation parameters, and the agent executes the HTTP requests. This mechanism keeps your headless frontends synced with your backend data sources automatically.

Deep inspection of storage arrays.

Asset auditing requires deep inspection of storage arrays. Your agent calls `list_media_uploads` to map out image storage. It verifies specific file blocks using `get_media_upload`. Cleaning up stale assets is just as direct. The agent dispatches `wipe_media_upload` to clear disk space and `wipe_cms_record` to drop dead document rows. You define the cleanup logic in Vertex AI, and the agent executes the removals.

Setup guide

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

Initialize an `McpToolset` with your Vinkius HTTP endpoint URL. Pass this toolset to your `LlmAgent` constructor. The tools become immediately available to your Gemini models.

You pass a `tool_names` filter when setting up the toolset. This limits the agent to specific operations like `execute_graphql_cda` or `list_global_models`. It prevents the model from accidentally triggering destructive actions.

The agent uses `list_global_models` to read the structured rules. Gemini's massive context window holds the entire schema definition in memory. This allows the model to generate perfectly formatted payloads for write operations.

The SDK supports both Stdio and HTTP transports natively. You use the `StreamableHttpServerParameters` class to connect to the managed Vinkius instance. The connection handles auth via your single endpoint token.

The sandbox isolates your file blocks, media URLs, and document rows completely. Vinkius spins up an ephemeral environment for the task and tears it down immediately. Your enterprise data never touches our permanent storage.

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