How to Use the Amplience MCP in LlamaIndex

Q: Can I restrict which CMS tools the agent accesses?

Yes. You can use the allowedtools filter when passing the specification to your agent. This prevents read-only applications from accidentally triggering deletions or live updates.

Turn your Amplience MCP Server into a searchable vector store with LlamaIndex and query live e-commerce data instantly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amplience MCP to LlamaIndex

Create your Vinkius account to connect Amplience to LlamaIndex 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 Amplience with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live content for semantic search

LlamaIndex treats your CMS like a dynamic knowledge base. Instead of just reading text, your agent calls `list_content_items` to pull hundreds of product descriptions and immediately embeds them into a vector store. You can then query past configurations or localized marketing copy using natural language. Grounding your AI in actual API data prevents hallucinations. When a user asks about a specific promotional banner, the system uses `get_content_item` to fetch the exact schema revision. The response relies entirely on real database entries rather than guessed information.

Map environments with this MCP Server

Understanding your CMS architecture is the first step for any RAG application. The integration starts by running `list_hubs` to identify all accessible environments. It then maps the internal structure by calling `list_repositories` and `list_folders`, building a complete index of where every asset lives. This structural awareness makes filtering highly accurate. If you only want to search through the UK holiday campaign folder, the agent knows exactly which repository ID to target. It pulls only the relevant documents before generating an answer.

Verify live CDN deployments

Building applications on top of e-commerce data requires knowing what customers actually see. Your setup can execute `get_delivery_content` to retrieve the structural blocks directly from the delivery edge. This confirms whether a recent update actually made it to production. Creating new records based on those insights takes seconds. If the semantic search reveals missing product details, the agent formats the missing data and fires `create_content_item` to fill the gap. You can even update existing structures with `update_content_item` based on retrieved context.

Setup guide

Set up Amplience MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Amplience MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Amplience tools.",
)
response = await agent.run("List recent Amplience data")

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 Amplience. 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 Amplience 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 Amplience MCP in LlamaIndex

Install llama-index-tools-mcp and initialize a BasicMCPClient with your Vinkius URL. Wrap it in an McpToolSpec, convert it to an async tool list, and hand it to your FunctionAgent.

Absolutely. The agent queries all accessible environments, pulls the repository lists, and indexes the content items across your entire account for unified semantic search.

It does. Your RAG application can draft updates based on retrieved context and immediately trigger the publish tool to push those changes to the live delivery CDN.

Yes. You can use the allowed_tools filter when passing the specification to your agent. This prevents read-only applications from accidentally triggering deletions or live updates.

We isolate every connection. The system reads your product copy, schema configurations, and folder hierarchies through a stateless, sandboxed environment. Nothing persists on our infrastructure after the RAG pipeline completes its query.

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