How to Use the Highnote MCP in LlamaIndex

Q: How do I configure the Highnote MCP Server in LlamaIndex?

Install llama-index-tools-mcp and set up a BasicMCPClient. You pass the client to McpToolSpec and await totoollistasync() to expose the tools.

Q: Can LlamaIndex search through Highnote account holders?

Yes. You use the listaccountholders tool to pull individuals and businesses into your index. Your agent can then run semantic searches to find specific IDs.

Q: Does LlamaIndex hallucinate card statuses?

No. The agent queries the live API using getpaymentcarddetails. It bases its response entirely on the actual JSON returned by the endpoint.

Q: How do I filter which tools the agent can use?

You apply the allowedtools filter when configuring your FunctionAgent. This restricts the agent to specific read-only tools like listcardproducts.

Index Highnote ledger entries and card data directly into LlamaIndex to build queryable financial knowledge bases.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Highnote MCP to LlamaIndex

Create your Vinkius account to connect Highnote 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 Highnote with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Financial Accounts

The `list_financial_accounts` tool allows your LlamaIndex agent to pull raw balance data and map it directly into your vector store. You run a daily sync that grabs every active account and its current standing. Your RAG application then queries this live snapshot instead of relying on stale documentation. When a user asks about account distribution, the agent retrieves the exact figures from the index. It combines the output from `get_financial_account` with your internal policies to generate answers grounded in real math, completely eliminating hallucination risks.

Searchable Transaction Histories

The `list_financial_transactions` tool feeds spending records into your semantic search pipeline. Your LlamaIndex application embeds these transaction descriptions and merchant codes. You can now search your entire processing history using natural language queries like 'find all fleet fuel purchases from last week.' If a specific charge looks weird, the agent pulls the exact metadata using `get_transaction_details`. It cross-references the API response with your indexed fraud guidelines. You get a direct answer based on the actual ledger.

LlamaIndex MCP Server for Card Management

The `list_payment_cards` tool surfaces every physical and virtual card attached to your program. Your agent indexes expiration dates and current statuses. You build an application that alerts you when a large batch of consumer cards nears expiration. You can also take action directly from the prompt. The agent uses `update_card_status` to push a CLOSED state to specific cards identified in your search results. You manage your entire issuance program through a single query interface.

Setup guide

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

Install `llama-index-tools-mcp` and set up a `BasicMCPClient`. You pass the client to `McpToolSpec` and await `to_tool_list_async()` to expose the tools.

Yes. You use the `list_account_holders` tool to pull individuals and businesses into your index. Your agent can then run semantic searches to find specific IDs.

No. The agent queries the live API using `get_payment_card_details`. It bases its response entirely on the actual JSON returned by the endpoint.

You apply the `allowed_tools` filter when configuring your `FunctionAgent`. This restricts the agent to specific read-only tools like `list_card_products`.

The server handles sensitive merchant codes and ledger entries. The MCP connection runs through an ephemeral zero-trust sandbox, meaning your raw financial records stay isolated from the core LLM processing environment.

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