How to Use the Amplience MCP in AutoGen

Q: How do I configure AutoGen to use the Amplience MCP server?

Install autogen-extmcp and use mcpservertools with a StreamableHttpServerParams object. Pass the resulting tool list directly into your AssistantAgent constructor.

Let AutoGen agents debate, draft, and deploy via the Amplience MCP server through consensus-driven workflows.

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 AutoGen

Create your Vinkius account to connect Amplience to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent consensus for content creation

Complex CMS tasks require deliberation. You can spin up a drafting agent that uses `create_content_item` to propose a new product page, while a separate compliance agent reviews the output. They argue over the exact JSON structure until both agree it matches your brand guidelines perfectly. This negotiation happens autonomously. If the compliance agent spots a schema error, it rejects the draft. The drafting agent then runs `update_content_item` to fix the mistake, continuing the loop until the final structure is flawless.

Safe deletions via this MCP Server

Wiping out database records should never be a unilateral decision. A designated security agent can take charge of the `delete_content_item` tool. When another agent requests a removal, the security persona forces a version validation check first. Gathering the necessary context for these decisions is simple. The reviewing agent calls `get_content_item` to inspect the revision lock. Only after confirming the item is safe to remove will the team reach a consensus and execute the final deletion command.

Coordinate live deployments and edge verification

Pushing to production involves multiple checks. Your deployment agent triggers `publish_content_item` to send an approved version to the live delivery CDN. It acts only after the editing agents finish their debate and sign off on the final copy. A separate QA agent handles the aftermath. It immediately runs `get_delivery_content` to read the exact structural blocks from the edge. If the live version doesn't match the approved draft, the QA agent alerts the team to start troubleshooting the discrepancy.

Setup guide

Set up Amplience MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Amplience tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Amplience_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Amplience data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Amplience_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Amplience data")
    print(result.messages[-1].content)

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 AutoGen

Install autogen-ext[mcp] and use mcp_server_tools with a StreamableHttpServerParams object. Pass the resulting tool list directly into your AssistantAgent constructor.

They share the same toolset. You define which specific agents have permission to call the read tools versus the write tools, allowing them to collaborate securely on the same repository.

The adapter automatically converts the CMS schemas into a format the agents understand. If an update fails, the error feeds back into the conversation so the agents can debate the fix and try again.

The setup relies on Streamable HTTP transports. It maintains a reliable connection to the Vinkius endpoint while your agents deliberate over long-running content generation tasks.

Your delivery blocks, repository IDs, and draft copy never touch persistent storage. The V8 Isolate Sandbox destroys the execution environment entirely the moment your agent conversation terminates.

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