How do I find my Arrivy API Key?

Log in to your Arrivy account, go to **Settings > Integrations**, and you will find your API Key under the **Developer** or **API** section.

Can I assign a crew to a task via this server?

Yes, you can use the `update_task` tool and provide the crew IDs in the update body to assign or reassign tasks.

Does Arrivy support real-time ETAs?

Yes, Arrivy calculates real-time ETAs based on field personnel location. You can retrieve these via the `get_task` or `list_locations` tools.

Arrivy MCP Server for LangChain 9 tools — connect in under 2 minutes

Name: Arrivy
Availability: InStock
Author: Vinkius

python.langchain.com/docs/integrations/tools/mcp

Built by Vinkius GDPR 9 Tools Framework

LangChain is the leading Python framework for composable LLM applications. Connect Arrivy through Vinkius and LangChain agents can call every tool natively. combine them with retrievers, memory, and output parsers for sophisticated AI pipelines.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MultiServerMCPClient({
        "arrivy": {
            "transport": "streamable_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,
        )
        response = await agent.ainvoke({
            "messages": [{
                "role": "user",
                "content": "Using Arrivy, show me what tools are available.",
            }]
        })
        print(response["messages"][-1].content)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Arrivy MCP Server

The Arrivy MCP Server empowers your AI agent to coordinate field operations and last-mile delivery directly from your workspace. Seamlessly manage your mobile workforce, track job progress, and engage with customers using natural language.

LangChain's ecosystem of 500+ components combines seamlessly with Arrivy through native MCP adapters. Connect 9 tools via Vinkius and use ReAct agents, Plan-and-Execute strategies, or custom agent architectures. with LangSmith tracing giving full visibility into every tool call, latency, and token cost.

Key Features

Task Orchestration — List, create, and update service tasks or delivery jobs with real-time status tracking.
Crew Management — Monitor field personnel and resource assignments to ensure efficient job allocation.
Customer Engagement — Manage customer records and sync service history for better communication.
Location Tracking — Access real-time location data and ETAs for your field technicians and delivery drivers.
Digital Workflow — Access data captured in the field, including forms, photos, and status updates.
Seamless Integration — Connect your Arrivy operations with your AI-assisted project management and support workflows.

Benefits for Teams

Operations Managers — Quickly audit active jobs and crew statuses without leaving your AI dashboard.
Dispatchers — Use AI to quickly create and assign new tasks based on customer requests.
Customer Success — Retrieve job history and ETAs instantly to provide accurate updates to clients.

The Arrivy MCP Server exposes 9 tools through the Vinkius. Connect it to LangChain in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Arrivy to LangChain via MCP

Follow these steps to integrate the Arrivy MCP Server with LangChain.

Install dependencies

Run pip install langchain langchain-mcp-adapters langgraph langchain-openai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save the code and run python agent.py

Explore tools

The agent discovers 9 tools from Arrivy via MCP

Why Use LangChain with the Arrivy MCP Server

LangChain provides unique advantages when paired with Arrivy through the Model Context Protocol.

The largest ecosystem of integrations, chains, and agents. combine Arrivy MCP tools with 500+ LangChain components

Agent architecture supports ReAct, Plan-and-Execute, and custom strategies with full MCP tool access at every step

LangSmith tracing gives you complete visibility into tool calls, latencies, and token usage for production debugging

Memory and conversation persistence let agents maintain context across Arrivy queries for multi-turn workflows

Arrivy + LangChain Use Cases

Practical scenarios where LangChain combined with the Arrivy MCP Server delivers measurable value.

RAG with live data: combine Arrivy tool results with vector store retrievals for answers grounded in both real-time and historical data

Autonomous research agents: LangChain agents query Arrivy, synthesize findings, and generate comprehensive research reports

Multi-tool orchestration: chain Arrivy tools with web scrapers, databases, and calculators in a single agent run

Production monitoring: use LangSmith to trace every Arrivy tool call, measure latency, and optimize your agent's performance

Arrivy MCP Tools for LangChain (9)

These 9 tools become available when you connect Arrivy to LangChain via MCP:

create_customer

Create a new customer record

create_task

Create a new service task in Arrivy

get_account_check

Verify Arrivy account connection

get_task

Get details for a specific task

list_crews

List all field crews and personnel

list_customers

List all customers in the system

list_locations

List all tracked locations

list_tasks

List all service tasks in Arrivy

update_task

Update an existing service task

Example Prompts for Arrivy in LangChain

Ready-to-use prompts you can give your LangChain agent to start working with Arrivy immediately.

"List all scheduled tasks for today in Arrivy."

"Create a new task 'Emergency Leak Repair' at '123 Maple St'."

"Show me the status of task ID 'T12345'."

Troubleshooting Arrivy MCP Server with LangChain

Common issues when connecting Arrivy to LangChain through the Vinkius, and how to resolve them.

MultiServerMCPClient not found

Install: pip install langchain-mcp-adapters

Arrivy + LangChain FAQ

Common questions about integrating Arrivy MCP Server with LangChain.

How does LangChain connect to MCP servers?

Use langchain-mcp-adapters to create an MCP client. LangChain discovers all tools and wraps them as native LangChain tools compatible with any agent type.

Which LangChain agent types work with MCP?

All agent types including ReAct, OpenAI Functions, and custom agents work with MCP tools. The tools appear as standard LangChain tools after the adapter wraps them.