How to Use the All Digital Rewards MCP in AutoGen

Q: How can I set up multiple AutoGen agents to manage an All Digital Rewards program?

You create separate AssistantAgent instances for each role you need, like a 'CampaignManager' and a 'ParticipantAdmin'. You give each agent access to the specific All Digital Rewards tools they need to do their job, then have them collaborate in a GroupChat.

Q: Can one AutoGen agent create a participant and another agent award them points?

Yes, that's a core pattern. The first agent calls createparticipant and posts the new user's ID into the shared conversation. A second agent sees that message, extracts the ID, and then uses it to call issuepoints.

Q: How do I give different All Digital Rewards tools to different agents in AutoGen?

After you get the full tool list from mcpservertools, you filter it. When you create each AssistantAgent, you pass only the function definitions for the tools that agent is allowed to use, like giving issuepoints to one agent and listorders to another.

Let specialized AI agents debate and manage your All Digital Rewards programs with AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect All Digital Rewards MCP to AutoGen

Create your Vinkius account to connect All Digital Rewards 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 All Digital Rewards with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-Driven Point Awards

With AutoGen, you create a team of agents that collaborate. For instance, a 'GiftingAgent' could propose giving a user 1,000 points by calling `issue_points`. But a 'BudgetAgent' in the same conversation can check the program's balance with `get_program_details` and counter the proposal if it's too high. They debate until they reach a consensus. The user is just the manager who gives the initial instruction, like 'reward our top contributor'. The agents handle the negotiation and execution, ensuring actions align with your rules.

Design Programs with a Multi-Agent AutoGen Team

Setting up a new rewards program involves multiple roles. You can model this with AutoGen. A 'CreativeAgent' can call `list_reward_products` to brainstorm ideas. An 'AdminAgent' can use `create_participant` to enroll a test group. A 'ComplianceAgent' can double-check the details against your internal rules. These agents work together in a group chat, each contributing its specialty. This multi-agent approach lets you automate complex, collaborative workflows that would be impossible with a single agent. The MCP Server provides the tools each agent needs to do its job.

Automate Order Auditing and Support

You can build an autonomous auditing team. An 'AuditAgent' could run `list_orders` every hour to look for transactions with a 'failed' status. When it finds one, it doesn't just send an alert—it starts a conversation with a 'SupportAgent'. The 'SupportAgent' then uses `get_participant_details` and `get_order_details` to investigate the specific failure. The two agents discuss the findings and can decide whether to retry the order or escalate to a human with a complete summary of what they found. It's a proactive way to manage fulfillment.

Setup guide

Set up All Digital Rewards 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 All Digital Rewards 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="All Digital Rewards_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent All Digital Rewards 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="All Digital Rewards_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent All Digital Rewards 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 All Digital Rewards. 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 All Digital Rewards 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 All Digital Rewards MCP in AutoGen

You create separate `AssistantAgent` instances for each role you need, like a 'CampaignManager' and a 'ParticipantAdmin'. You give each agent access to the specific All Digital Rewards tools they need to do their job, then have them collaborate in a `GroupChat`.

Yes, that's a core pattern. The first agent calls `create_participant` and posts the new user's ID into the shared conversation. A second agent sees that message, extracts the ID, and then uses it to call `issue_points`.

After you get the full tool list from `mcp_server_tools`, you filter it. When you create each `AssistantAgent`, you pass only the function definitions for the tools that agent is allowed to use, like giving `issue_points` to one agent and `list_orders` to another.

It's a conversation in plain text. One agent might output a message saying 'Proposing to call `issue_points` with amount=500.' Another agent can reply, 'Negative. The result from `get_program_details` shows the budget is low. Proposing amount=100.' They continue until they agree on a final action.

The data, like program metadata or participant profiles, is handled by the Vinkius MCP Server inside an ephemeral sandbox for each request. The data is passed back to your AutoGen agents, which operate in your own environment. You control the visibility of the conversation history between them.

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