How to Use the Hygraph (Headless CMS) MCP in Google ADK

Q: Can I restrict which Hygraph (Headless CMS) MCP tools are exposed to my Google ADK agent?

You can use the toolnames filter when initializing your McpToolset in Python. This lets you restrict the Google ADK agent's capabilities, exposing only read tools like executegraphqlquery while hiding destructive tools like wipecmsdocument.

Q: How does the Google ADK handle large media payloads from the CMS?

The agent calls listmediaassets to retrieve structured metadata, URLs, and file sizes instead of raw binaries. This allows your Google ADK agent to process media references efficiently or pass them to Vertex AI vision models.

Connect Google ADK enterprise agents to Hygraph (Headless CMS) to process long-context content and direct schema writes.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hygraph (Headless CMS) MCP to Google ADK

Create your Vinkius account to connect Hygraph (Headless CMS) 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 Hygraph (Headless CMS) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Process large content catalogs with Google ADK

Running `list_media_assets` and `execute_graphql_query` pulls rich media metadata and deep content trees directly into your enterprise agent's context. Gemini's massive token window allows your enterprise agent to digest entire content directories in one go. You can feed raw documentation or product databases into Gemini, letting the model determine how to restructure your headless schema. The agent can process complex relationships between thousands of items without hitting context limits.

Direct schema writes from BigQuery data pipelines

Invoking `execute_graphql_mutation` alongside `create_cms_document` lets your agent translate structured database rows into clean CMS writes. When your BigQuery pipelines signal updates, your Google ADK agent can execute mutations to update your CMS records in real time. Using these tools, the agent writes updates directly to your models. This eliminates the need for writing fragile, custom glue code between Google Cloud and your MCP Server setup.

Automate global content localization at scale

Querying `list_project_locales` allows your agent to check which languages your project supports before running translation tasks. Your agent can query active locales, then translate source texts using Vertex AI translation models. To push the updates live, the agent triggers `publish_cms_document` for each translated node. This architecture lets you build an automated translation desk that respects your strict CMS localization rules.

Setup guide

Set up Hygraph (Headless CMS) 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 Hygraph (Headless CMS) 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="Hygraph (Headless CMS)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Hygraph (Headless CMS) 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 Hygraph. 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 Hygraph (Headless CMS) 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 Hygraph (Headless CMS) MCP in Google ADK

Install the google-adk package, then initialize McpToolset with your Vinkius HTTP endpoint. Pass this toolset directly into your LlmAgent constructor to expose available tools like `execute_graphql_query` to your Gemini model.

Yes, by using the schema tools provided by the server. Your Google ADK agent can call `get_model_fields` to inspect the schema layout before making any modifications to your Hygraph (Headless CMS) project.

You can use the tool_names filter when initializing your McpToolset in Python. This lets you restrict the Google ADK agent's capabilities, exposing only read tools like `execute_graphql_query` while hiding destructive tools like `wipe_cms_document`.

The agent calls `list_media_assets` to retrieve structured metadata, URLs, and file sizes instead of raw binaries. This allows your Google ADK agent to process media references efficiently or pass them to Vertex AI vision models.

All interactions with your draft documents occur within a secure, ephemeral MCP sandbox. Vinkius manages your API credentials outside of the agent's direct context, ensuring your Google ADK never exposes sensitive Hygraph (Headless CMS) tokens during 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