How to Use the All Digital Rewards MCP in LangChain

Q: Can my LangChain agent manage multiple reward programs at once?

Yes. The agent can call listprograms to get the IDs of all active programs. From there, its logic can decide which program to act on, using the program ID in subsequent calls to tools like getprogramdetails or listparticipants.

Build multi-step reward automation agents that run on their own with All Digital Rewards and LangChain.

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 LangChain

Create your Vinkius account to connect All Digital Rewards to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Reward Operations Together

This isn't about calling one tool at a time. Your LangChain agent can build sequences of operations against the All Digital Rewards API. It can `list_programs` to find the right campaign, `list_participants` to get a list of users, and then loop through them to `issue_points`—all in one autonomous chain. You give the agent a high-level goal, and it figures out the steps. It might check on a user with `get_participant_details`, see they're new, and decide to use `create_participant` before doing anything else. LangSmith gives you a full trace of the agent's reasoning, showing exactly which tools were called with what data.

Build Smarter Reward Agents with LangChain

An agent can do more than just execute a list of commands. With LangChain's ReAct model, your agent can reason about the data it gets back from the All Digital Rewards server. It's the difference between a script and an assistant. For example, your agent could use `get_order_details` and see an order failed. Instead of just stopping, it could then decide to check `get_product_details` to see if the item is out of stock or check `get_participant_details` to see if the user's account is active. It makes decisions based on the live state of your rewards program.

Interact with Catalogs and Orders

Give your agent the tools to browse and manage your rewards catalog. It can fetch the entire catalog with `list_reward_products`, pull specifics with `get_product_details`, and then present the options to a user. It's a simple way to build a conversational rewards bot. Once a reward is chosen, the agent can track it. It uses `list_orders` to find the right transaction and then polls `get_order_details` for the fulfillment status. The whole process is a chain of tool calls, visible and debuggable right in LangSmith.

Setup guide

Set up All Digital Rewards MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes All Digital Rewards tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "all-digital-rewards-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent All Digital Rewards transactions"
    })
    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 LangChain

You don't have to manually chain them. Just pass the full list of tools from this MCP Server to the `create_agent` function. The agent's reasoning logic will automatically select and sequence the right tools, like `create_participant` then `issue_points`, based on your prompt.

Yes. The agent can call `list_programs` to get the IDs of all active programs. From there, its logic can decide which program to act on, using the program ID in subsequent calls to tools like `get_program_details` or `list_participants`.

Use LangSmith. Every tool call your agent makes to the All Digital Rewards MCP Server is traced, showing you the exact inputs, outputs, latency, and token count for each step in the chain. It makes finding issues in complex agentic workflows much easier.

You'd give your agent a prompt like 'Enroll user john.doe@email.com and give them 100 starter points.' The agent will know to first call `create_participant`, get the new participant ID from the result, and then use that ID to make a second call to `issue_points`.

Your agent communicates with the MCP Server using a single, secure Vinkius token. All requests that handle participant profiles or order details are executed in a V8 Isolate sandbox that is destroyed after your call completes. Vinkius manages the secure connection; your agent just gets the data.

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