How to Use the Arrivy MCP in Claude Code

Q: What's the command to connect the Arrivy MCP Server to Claude Code?

The command is claude mcp add --transport http arrivy-mcp -- . After that, run claude mcp list to confirm the Arrivy server is connected and its tools are available.

Pipe Arrivy data into your shell scripts and CI/CD jobs with Claude Code. Automate reports, create tasks from cron jobs, and manage your field ops from the terminal.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Arrivy MCP to Claude Code

Create your Vinkius account to connect Arrivy to Claude Code 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 Arrivy with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Field Operations with Shell Scripts

This is what a CLI-based MCP Server is for. You can now script any Arrivy operation. A simple bash script can call `list_tasks` with a query for unassigned jobs and pipe the output to an alert if anything is waiting. You can also automate creation. For example, set up a cron job that runs a script to `create_task` for recurring maintenance jobs every Monday morning. It's headless automation for your logistics.

Build Custom CI/CD and DevOps Pipelines

Integrate Arrivy operations into your existing pipelines. After a new customer signs up via your website, a GitHub Action could trigger Claude Code to run `create_customer` in Arrivy automatically. You can also build operational health checks. A simple pipeline can run `get_account_check` to confirm the connection is live, then use `list_crews` to make sure all expected crews are active, and send a failure notice if not. This is a powerful use of an MCP server in a DevOps context.

Query and Manage Arrivy from the Command Line

Sometimes you just need a quick answer. Run `claude mcp query arrivy-mcp 'list all tasks for today'` and get a clean, scriptable list of tasks directly in your terminal. You can pipe the JSON or text output to `jq`, `grep`, or anything else. This MCP server makes Arrivy feel like a native CLI tool. The same goes for making changes. Use `claude mcp exec arrivy-mcp 'update task 123 to status complete'` to modify a job without leaving your command line. It's faster than opening a browser and clicking through a UI.

Setup guide

Set up Arrivy MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see arrivy-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Arrivy transactions." It will automatically discover and invoke the available Arrivy tools.

Terminal

claude mcp add --transport http arrivy-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Arrivy MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "arrivy-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Arrivy. 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 Arrivy 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 Arrivy MCP in Claude Code

Once connected, you can call Arrivy tools from any script using `claude mcp exec arrivy-mcp ''`. For example, `claude mcp exec arrivy-mcp 'list_customers'` will output a JSON list of your customers that you can then process.

Yes. You just need to install Claude Code in your runner and provide the auth token as a secret. Then you can run commands like `create_task` as a step in your workflow, for example, to create a deployment task in Arrivy.

The command is `claude mcp add --transport http arrivy-mcp -- `. After that, run `claude mcp list` to confirm the Arrivy server is connected and its tools are available.

Yes. Claude Code is designed for scripting, so you can easily get raw JSON back from tools like `list_tasks` or `get_task`. This makes it easy to pipe the data to other command-line tools like `jq` for filtering and transformation.

Your connection to the Arrivy MCP Server is authenticated using a single Vinkius endpoint token, which you should store as an environment secret. This token isolates access, and the ephemeral sandbox ensures that no customer, task, or crew data persists on the server after your command finishes.

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