How to Use the Contentful MCP in Google ADK

Q: Can I restrict Google ADK to only read Contentful data without making edits?

Yes, you can pass a toolnames filter when initializing the McpToolset in Python. By excluding write tools from the MCP Server toolset, you ensure the Google ADK agent can only read content.

Q: How do I target a specific Contentful sandbox?

Your agent runs listenvironments to find the target sandbox ID. It then passes that environment ID to tools like listentries or createentry to keep development work isolated from production.

Feed Contentful data directly to Google ADK agents to power long-context Gemini workflows and BigQuery pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Contentful MCP to Google ADK

Create your Vinkius account to connect Contentful 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 Contentful with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed Gemini long-context with Contentful MCP Server data

Google ADK allows Gemini to hold millions of tokens in its context window, making it easy to digest your entire content library. Your agent can call `list_entries` and `list_assets` to pull massive batches of content straight from Contentful into the model's active memory. Instead of chunking articles into tiny pieces, you pass whole collections of entries. Gemini analyzes historical content patterns, checks existing structures via `list_content_types`, and writes new drafts that fit your exact style.

Connect BigQuery insights to Contentful publishing

Google ADK lets your agent query performance data in BigQuery and immediately update your website. The agent identifies low-performing pages, calls `get_entry` to inspect the current copy, and runs `update_entry` to revise the text based on SQL analysis. Once the updates are written, the agent executes `publish_entry` to push the changes live. This MCP Server handles the actual API payload translation so your pipeline never stalls.

Organization-wide asset and space management

Large Google Cloud deployments often span multiple teams and environments. Google ADK uses `list_organizations` and `list_spaces` to map out your entire digital footprint before making any changes. The agent can locate specific sandboxes using `list_environments` to test content updates safely. It ensures assets are uploaded to the correct environment before running `create_entry` in production.

Setup guide

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

Yes, you can pass a `tool_names` filter when initializing the `McpToolset` in Python. By excluding write tools from the MCP Server toolset, you ensure the Google ADK agent can only read content.

Gemini's massive context window easily handles large JSON payloads from `list_entries`. The Google ADK parses the tool output directly into the model's context, avoiding truncation issues common in smaller models.

Absolutely. You can deploy your Google ADK agent as a serverless function and connect it to the MCP Server via HTTP transport to run scheduled content maintenance tasks.

Your agent runs `list_environments` to find the target sandbox ID. It then passes that environment ID to tools like `list_entries` or `create_entry` to keep development work isolated from production.

Vinkius manages your Contentful API keys in a zero-trust environment, decrypting them only inside an ephemeral runtime when an MCP tool is called. Your actual entry text and asset metadata flow directly to your Google Cloud environment without being logged or cached by Vinkius.

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