How to Use the HiDeliver MCP in LangChain

Q: What happens if a HiDeliver dispatch fails in LangChain?

The ReAct agent catches the error from createdelivery. It can then automatically retry the request or notify the user, depending on your prompt logic.

Wire HiDeliver directly into your LangChain agents to schedule pickups and track account balances.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HiDeliver MCP to LangChain

Create your Vinkius account to connect HiDeliver 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 HiDeliver with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build automated dispatch chains with this MCP Server

LangChain agents excel at sequential logic. When a user requests a courier, your ReAct agent can immediately trigger `create_delivery` to log a fresh pickup. You don't have to write custom API wrappers. The agent then evaluates the output. If the destination changes mid-transit, the same chain calls `update_delivery` to adjust active route parameters. LangSmith captures every token spent and latency metric during these handoffs.

Track transactions across ReAct pipelines

Financial oversight matters when autonomous agents book deliveries. By injecting the `get_account_balance` tool into your LangChain setup, the agent checks remaining cash thresholds before committing to a dispatch. If the balance drops too low, the chain can halt execution or query `list_transactions` to audit recent ledger events. This prevents runaway loops from draining your HiDeliver budget.

Manage active delivery traces

Long-running LangChain sessions need current state data. Your agent pulls active requests using `list_deliveries` and filters them based on user prompts. If a customer decides to abort, the agent grabs the exact trace via `get_delivery` and immediately executes `cancel_delivery`. You get a clean, observable workflow without leaving your LangChain environment.

Setup guide

Set up HiDeliver 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 HiDeliver 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({
    "hideliver-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 HiDeliver 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 HiDeliver. 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 HiDeliver 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 HiDeliver MCP in LangChain

Install the langchain-mcp-adapters package. Wrap the HiDeliver endpoint using MultiServerMCPClient and pass the returned tools to your create_agent function.

Yes. LangSmith automatically traces every tool invocation. You can monitor the exact latency and token usage when your agent calls `get_transaction`.

The ReAct agent catches the error from `create_delivery`. It can then automatically retry the request or notify the user, depending on your prompt logic.

By default, the client is stateless. You must use client.session() to keep track of active route parameters between `get_delivery` calls.

Your agent accesses sensitive route parameters and API key transactions. We isolate these requests in a strict V8 sandbox, ensuring your ledger events never leak into shared memory.

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