How to Use the Bold MCP in LlamaIndex

Q: Can I index Bold transaction histories into LlamaIndex?

Yes, you can fetch your transaction logs using listtransactions and ingest them into your vector database. This lets your LlamaIndex agent perform semantic searches over past Colombian COP payments.

Q: How does this MCP Server help LlamaIndex agents check Bold terminal status?

The agent can invoke listterminals to pull live serial numbers and connection states. It inserts this real-time hardware status directly into the LLM context window to answer user queries accurately.

Q: Can LlamaIndex trigger physical Bold terminal payments?

Yes, your agent can call initiateterminalpayment when a user requests a physical checkout. It passes the target terminal's serial number and the transaction amount in Colombian Pesos to start the payment.

Q: How do I handle Bold payment refunds in LlamaIndex?

Your agent can issue a refund by calling refundpayment with the transaction ID. LlamaIndex can then index the updated transaction state via gettransaction to confirm the refund process has started.

Index your Bold Colombian transaction history and terminal status into LlamaIndex using this dedicated MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bold MCP to LlamaIndex

Create your Vinkius account to connect Bold 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 Bold with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build semantic search over Colombian transaction data

LlamaIndex allows your agent to perform semantic searches over past Colombian Peso payments by indexing the output of `list_transactions`. Feed your raw transaction logs directly into your vector store so your agent can query past Colombian Peso payments using natural language. Instead of writing complex SQL queries to find a past charge, your agent uses `get_transaction` to retrieve the exact settlement details. It then parses the metadata, turning structured financial events into searchable context for your RAG pipeline.

Ground LlamaIndex agent responses in live terminal status

This MCP Server lets your LlamaIndex agent call `list_terminals` to fetch the real-time connectivity status and serial numbers of your fleet in Colombia. Grounding your financial agents in active hardware telemetry prevents them from hallucinating device statuses. When a user asks why a payment failed, the agent combines local documentation with live data from `list_payment_methods` and `get_online_payment`. The resulting response is grounded in actual API states rather than static training data.

Automate payment link reconciliation via RAG

Your agent can run `get_payment_link` to pull the active COP amount and reference description, embedding this data directly into the current conversation index. This lets you reconcile open invoices by indexing active payment links and checking them against customer queries. If a customer claims they paid, the agent uses `list_webhooks` to verify if a payment notification was received. If missing, it can instantly run `create_payment_link` to generate a new checkout URL and update the vector index with the new reference.

Setup guide

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

Yes, you can fetch your transaction logs using `list_transactions` and ingest them into your vector database. This lets your LlamaIndex agent perform semantic searches over past Colombian COP payments.

The agent can invoke `list_terminals` to pull live serial numbers and connection states. It inserts this real-time hardware status directly into the LLM context window to answer user queries accurately.

Yes, your agent can call `initiate_terminal_payment` when a user requests a physical checkout. It passes the target terminal's serial number and the transaction amount in Colombian Pesos to start the payment.

Your agent can issue a refund by calling `refund_payment` with the transaction ID. LlamaIndex can then index the updated transaction state via `get_transaction` to confirm the refund process has started.

Your card tokens, Colombian anti-fraud customer details, and COP transaction amounts are never cached or stored by Vinkius. The MCP Server operates inside an isolated, ephemeral V8 container, ensuring that sensitive financial data stays between your LlamaIndex agent and the secure payment gateway.

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