How to Use the Kargo MCP in LlamaIndex

Q: How do I add Kargo tools to LlamaIndex?

Install llama-index-tools-mcp and initialize a BasicMCPClient. Wrap it with McpToolSpec and pass the resulting tool list to your FunctionAgent.

Q: Can LlamaIndex cache Kargo API responses?

Yes. You can index the output of tools like listfacilities into your vector store. Your application queries the local index for general questions and only calls the live MCP Server for real-time status checks.

Q: Does LlamaIndex support Kargo data access?

Set includeresources=True when configuring the tool spec. This allows your agent to read underlying logistics payloads directly from the server.

Q: How do I restrict which tools the agent uses?

Use the allowedtools filter during setup. You can give the agent read-only access by exposing getshipment while hiding write operations.

Index Kargo logistics data into LlamaIndex to query your loading docks via 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 Kargo MCP to LlamaIndex

Create your Vinkius account to connect Kargo 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 Kargo with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index active freight records

You pull every active load using `list_shipments` and feed the results straight into a LlamaIndex vector store. The agent reads the raw API output and converts those logistics records into searchable document nodes. Now your team can ask natural language questions about dock congestion. The RAG pipeline queries the index instead of hitting the live API for every single user message. You get instant answers grounded in actual freight data.

Query specific order context

When a user asks about a delayed truck, your FunctionAgent triggers `get_order` to pull the exact manifest. It combines this fresh data with historical routing guides you already indexed. This Kargo MCP Server integration bridges the gap between static documents and live operations. You give the LLM the tools to fetch missing context on the fly. It reads `get_carrier_info` to find the driver's phone number and includes it in the response.

Search your Kargo MCP Server logs

The `list_payload_logs` tool lets your agent index recent sync events directly into your workspace. If a dispatcher reports a missing update, the RAG app searches the recent payload history to find the exact failure point. You do not have to manually dig through JSON responses. The agent runs `get_device_status` to check the hardware, compares it against the indexed logs, and tells you why the gate did not open.

Setup guide

Set up Kargo 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 Kargo 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 Kargo tools.",
)
response = await agent.run("List recent Kargo 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 Kargo. 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 Kargo 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 Kargo MCP in LlamaIndex

Install `llama-index-tools-mcp` and initialize a `BasicMCPClient`. Wrap it with `McpToolSpec` and pass the resulting tool list to your `FunctionAgent`.

Yes. You can index the output of tools like `list_facilities` into your vector store. Your application queries the local index for general questions and only calls the live MCP Server for real-time status checks.

Set `include_resources=True` when configuring the tool spec. This allows your agent to read underlying logistics payloads directly from the server.

Use the `allowed_tools` filter during setup. You can give the agent read-only access by exposing `get_shipment` while hiding write operations.

All requests flow through a zero-trust architecture. When LlamaIndex fetches specific order details or manifests, the system authenticates via a single endpoint token. We drop all credentials immediately after the request resolves.

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