Can the agent push updates without breaking my Amplience JSON schemas?

Yes. Before invoking the update tool, the agent utilizes context to retrieve the item's precise configuration. It parses the associated Schema ID requirements and injects the updated stringified payload adhering identically to Amplience's validation rules.

Will the integration protect my items against concurrent manipulation issues?

Yes. Our Amplience server requires the agent to explicitly pass the exact `version` lock integer on every DELETE or UPDATE request. If a human colleague alters your CMS page while the agent is typing, the AI request is robustly rejected avoiding fatal overwrites.

Can I publish a finalized post straight to the Edge Delivery API from here?

Absolutely. Once the content looks solid offline, just declare 'Publish this content item now.' The agent resolves the `publish_content_item` tool pointing to your Edge API and the post lives dynamically on your core frontend instantly.

Amplience MCP Server for Google ADK 10 tools — connect in under 2 minutes

Name: Amplience
Availability: InStock
Author: Vinkius

google.github.io/adk-docs/tools/mcp-tools

Built by Vinkius GDPR 10 Tools SDK

Google Agent Development Kit (ADK) is Google's framework for building production AI agents. Add Amplience as an MCP tool provider through Vinkius and your ADK agents can call every tool with full schema introspection.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from google.adk.agents import Agent
from google.adk.tools.mcp_tool import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import (
    StreamableHTTPConnectionParams,
)

# Your Vinkius token. get it at cloud.vinkius.com
mcp_tools = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    )
)

agent = Agent(
    model="gemini-2.5-pro",
    name="amplience_agent",
    instruction=(
        "You help users interact with Amplience "
        "using 10 available tools."
    ),
    tools=[mcp_tools],
)

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Amplience MCP Server

Link your Amplience headless CMS to any intelligent AI agent to completely rethink how you handle your enterprise content architecture, deploying components natively through standard conversation.

Google ADK natively supports Amplience as an MCP tool provider. declare Vinkius Edge URL and the framework handles discovery, validation, and execution automatically. Combine 10 tools with Gemini's long-context reasoning for complex multi-tool workflows, with production-ready session management and evaluation built in.

What you can do

Discover Asset Hierarchies — Freely list top-level Hubs, target specific Repositories, and fetch internal Folders to help your AI inherently understand where every graphic and article lives.
Content Retrieval — Paginate through dynamic content items, safely extracting complete metadata alongside current active schemas and validation rules.
Edit & Create Structure — Give the agent full permission to push correctly strictly-typed JSON payloads back into the system, generating or modifying blog entries and product metadata.
Manage Deployments — Permanently execute deletions (if revision locks permit) or instruct the system to fire a specific content configuration directly over to the edge delivery API to hit the live website.

The Amplience MCP Server exposes 10 tools through the Vinkius. Connect it to Google ADK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Amplience to Google ADK via MCP

Follow these steps to integrate the Amplience MCP Server with Google ADK.

Install Google ADK

Run pip install google-adk

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Create the agent

Save the code above and integrate into your ADK workflow

Explore tools

The agent will discover 10 tools from Amplience via MCP

Why Use Google ADK with the Amplience MCP Server

Google ADK provides unique advantages when paired with Amplience through the Model Context Protocol.

Google ADK natively supports MCP tool servers. declare a tool provider and the framework handles discovery, validation, and execution

Built on Gemini models, ADK provides long-context reasoning ideal for complex multi-tool workflows with Amplience

Production-ready features like session management, evaluation, and deployment come built-in. not bolted on

Seamless integration with Google Cloud services means you can combine Amplience tools with BigQuery, Vertex AI, and Cloud Functions

Amplience + Google ADK Use Cases

Practical scenarios where Google ADK combined with the Amplience MCP Server delivers measurable value.

Enterprise data agents: ADK agents query Amplience and cross-reference results with internal databases for comprehensive analysis

Multi-modal workflows: combine Amplience tool responses with Gemini's vision and language capabilities in a single agent

Automated compliance checks: schedule ADK agents to query Amplience regularly and flag policy violations or configuration drift

Internal tool platforms: build self-service agent platforms where teams connect their own MCP servers including Amplience

Amplience MCP Tools for Google ADK (10)

These 10 tools become available when you connect Amplience to Google ADK via MCP:

create_content_item

Create a new structured content item adhering to a schema inside a folder

delete_content_item

Requires version validation before deletion. Permanently delete a content item from the repository database

get_content_item

Retrieve a specific content item configuration and its schema revision lock

get_delivery_content

Retrieve the exact structural matching verifying Delivery CDN blocks

list_content_items

Retrieve paginated content items from a specific repository

list_folders

List all folders organizing content in a given repository

list_hubs

Essential for retrieving the active workspace. List all accessible Amplience Hubs (environments)

list_repositories

List all content repositories within a specific Hub

publish_content_item

Publish a specific content item version to the live delivery CDN

update_content_item

Update an existing content item data structure matching its current schema

Example Prompts for Amplience in Google ADK

Ready-to-use prompts you can give your Google ADK agent to start working with Amplience immediately.

"Identify all active repositories present inside my default Amplience Hub."

"Pull the structural metadata (schema lock and payload) of item '5tYv92'."

"Publish the newly edited Content '5tYv92' to the global live network."

Troubleshooting Amplience MCP Server with Google ADK

Common issues when connecting Amplience to Google ADK through the Vinkius, and how to resolve them.

McpToolset not found

Update: pip install --upgrade google-adk

Amplience + Google ADK FAQ

Common questions about integrating Amplience MCP Server with Google ADK.

How does Google ADK connect to MCP servers?

Import the MCP toolset class and pass the server URL. ADK discovers and registers all tools automatically, making them available to your agent's tool-use loop.

Can ADK agents use multiple MCP servers?

Yes. Declare multiple MCP tool providers in your agent configuration. ADK merges all tool schemas and the agent can call tools from any server in a single turn.

Which Gemini models work best with MCP tools?

Gemini 2.0 Flash and Pro models both support function calling required for MCP tools. Flash is recommended for latency-sensitive use cases, Pro for complex reasoning.