How to Use the HiDeliver MCP in LlamaIndex

Q: Will the LlamaIndex agent hallucinate HiDeliver account balances?

No. When users ask about remaining tokens, the agent calls getaccountbalance directly. It grounds the final answer in the exact numbers returned by the API.

Q: Can I restrict which HiDeliver tools LlamaIndex accesses?

You can pass an allowedtools filter when building the spec. This prevents the agent from calling canceldelivery if you only want read-only access.

Index HiDeliver transactions and route parameters directly into LlamaIndex for queryable RAG applications.

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 LlamaIndex

Create your Vinkius account to connect HiDeliver 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 HiDeliver with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ground RAG queries in live delivery data

LlamaIndex transforms raw API output into searchable knowledge. When you connect this MCP Server, your RAG application can pull active requests via `list_deliveries` and embed them into your vector store. Users can then ask natural language questions about their dispatch history. The FunctionAgent fetches the exact parameters using `get_delivery`, ensuring the response relies on actual route data instead of hallucinated tracking numbers.

Build semantic search for HiDeliver ledgers

Querying past billing events usually requires database access. With the `list_transactions` tool, LlamaIndex indexes global ledger events directly into your knowledge base. Your agent can isolate a single API key transaction using `get_transaction`. This lets internal teams query cash thresholds and historical spend without leaving their chat interface.

Modify active routes from LlamaIndex chat

Read-only RAG is just the start. Your LlamaIndex setup can take action on the indexed data by calling `create_delivery` to schedule a fresh pickup based on user commands. If the user needs to change a destination, the agent cross-references the embedded trace and executes `update_delivery`. If they want to abort, it triggers `cancel_delivery` to stop the mapped trace entirely.

Setup guide

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

Install llama-index-tools-mcp. Initialize BasicMCPClient with your endpoint, then convert it using mcp_tool_spec.to_tool_list_async() before passing it to your FunctionAgent.

Yes. You can configure the agent to pull historical records via `list_deliveries` and embed them into your index for semantic queries.

No. When users ask about remaining tokens, the agent calls `get_account_balance` directly. It grounds the final answer in the exact numbers returned by the API.

You can pass an allowed_tools filter when building the spec. This prevents the agent from calling `cancel_delivery` if you only want read-only access.

The integration processes raw cash thresholds and pickup coordinates. Vinkius runs the connection in an ephemeral, zero-trust container, destroying the memory state immediately after your RAG pipeline completes the query.

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