How to Use the Arrivy MCP in LlamaIndex

Q: How do I connect the Arrivy MCP Server to LlamaIndex?

Install llama-index-tools-mcp and initialize the BasicMCPClient with your Vinkius endpoint. Pass the client to McpToolSpec and call totoollistasync() to load the tools into your FunctionAgent.

Q: Can LlamaIndex agents write new tasks to Arrivy using this MCP setup?

Yes, your agent can write tasks. By exposing createtask and updatetask, the agent modifies schedules based on semantic queries or incoming document data.

Q: Can I filter which Arrivy tools are exposed to my agent?

Yes, you can use the allowedtools filter during initialization. This lets you restrict your agent to read-only tools like gettask and listcrews while hiding write operations.

Feed real-time Arrivy dispatch data and crew schedules directly into your LlamaIndex vector store for instant semantic search.

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 LlamaIndex

Create your Vinkius account to connect Arrivy to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ground LlamaIndex Agents in Live Arrivy Dispatch Operations

LlamaIndex uses the `list_tasks` and `list_crews` tools to pull live field dispatch data directly into its context window. This MCP Server exposes these operations directly to the framework, letting your agent query active work orders and crew assignments to turn raw API payloads into structured nodes. Instead of relying on stale CSV exports, the framework calls `get_task` to fetch real-time updates on specific jobs. This live connection ensures your RAG pipeline answers questions using current job statuses rather than outdated snapshots.

Semantic Search Over Field Crew Schedules

The `list_crews` tool exposes active field technician rosters and assignments to your LlamaIndex vector database. By embedding these personnel structures, your pipeline resolves natural language queries about who is working where without hardcoded SQL joins. When a dispatch emergency hits, the agent runs `list_locations` to locate nearby crews. It then updates the schedule instantly using `update_task`, writing the operational changes directly back to Arrivy.

Automated Customer and Task Creation via RAG

The `create_customer` tool lets your LlamaIndex FunctionAgent register new clients directly from incoming email text or transcribed support tickets. Using this MCP tool setup, your agent extracts the contact details, checks the connection status with `get_account_check`, and builds the record. Once the customer profile exists, the agent invokes `create_task` to schedule the job. This links your unstructured document parsing directly to Arrivy's field scheduling engine.

Setup guide

Set up Arrivy MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Arrivy MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Arrivy tools.",
)
response = await agent.run("List recent Arrivy data")

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 LlamaIndex

Install `llama-index-tools-mcp` and initialize the `BasicMCPClient` with your Vinkius endpoint. Pass the client to `McpToolSpec` and call `to_tool_list_async()` to load the tools into your `FunctionAgent`.

Yes, your agent can write tasks. By exposing `create_task` and `update_task`, the agent modifies schedules based on semantic queries or incoming document data.

The framework uses standard backoff strategies when executing tools like `list_tasks` or `list_customers`. Vinkius manages the underlying connection pool to keep execution latencies low.

Yes, you can use the `allowed_tools` filter during initialization. This lets you restrict your agent to read-only tools like `get_task` and `list_crews` while hiding write operations.

All tool executions run inside ephemeral V8 isolate sandboxes that instantly self-destruct after the API call completes. This zero-trust architecture ensures your sensitive customer addresses, crew coordinates, and task details are never stored or logged on Vinkius servers.

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