How to Use the Flip MCP in LlamaIndex

Q: How do I index Flip transaction histories in LlamaIndex?

You load the output of listdisbursements into a vector store using the LlamaIndex document parser. This lets your agent run semantic searches over past payouts to resolve vendor questions without querying the raw database every time. It turns API payloads into searchable knowledge.

Q: Can LlamaIndex agents check active Flip balances before paying bills?

Yes, your agent can call getbalance to retrieve live funds and index the result before executing a payout. This ensures the agent is grounded in actual financial figures before it attempts to run createdisbursement. It completely eliminates the risk of overdrafts caused by hallucinated balances.

Q: Can I filter which banks my agent can query?

Yes, you can use the allowedtools filter when registering the tool spec. If you only want your agent to read data, you can restrict its access to listbanks and getbill while blocking disbursement tools.

Q: How does LlamaIndex handle the privacy of transaction records?

Transaction records from listpayments and bank details from validatebankaccount are processed strictly in-memory during index generation. No financial credentials or customer bank account numbers are cached on external servers or used for model training.

Index live financial data into LlamaIndex to query past Flip payouts and bank records using 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 Flip MCP to LlamaIndex

Create your Vinkius account to connect Flip 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 Flip with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Convert live financial responses into searchable vector data

LlamaIndex doesn't just call `list_disbursements` or `list_payments`; it lets you index these transaction records directly into your vector store. Your agent can then perform semantic queries over your actual payout history instead of relying on static database exports. This turns raw API outputs into a dynamic knowledge base. When your agent needs to check if a specific vendor was paid, it queries the index of past `get_disbursement` payloads to find the exact match.

Build a financial RAG pipeline with LlamaIndex and MCP Server

Combine your offline invoice PDFs with live banking data retrieved via this MCP Server. Your agent can retrieve a PDF invoice, run `get_balance` to check available funds, and verify if the invoice matches current records. This architecture grounds your financial queries in real-time bank realities. It prevents your agent from hallucinating balances or trying to pay bills that have already been settled.

Ground agent decisions in verified bank directories

By indexing the output of `list_banks` and `list_cities`, your LlamaIndex agent always has access to verified routing destinations. It searches this local index to validate user inputs before attempting to call any transactional tools. This MCP step prevents runtime errors during payment creation. The agent checks the local vector index first, ensuring the target bank is supported before invoking `create_bill`.

Setup guide

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

You load the output of `list_disbursements` into a vector store using the LlamaIndex document parser. This lets your agent run semantic searches over past payouts to resolve vendor questions without querying the raw database every time. It turns API payloads into searchable knowledge.

Yes, your agent can call `get_balance` to retrieve live funds and index the result before executing a payout. This ensures the agent is grounded in actual financial figures before it attempts to run `create_disbursement`. It completely eliminates the risk of overdrafts caused by hallucinated balances.

You initialize the connection using the basic client and convert it to an MCP tool spec with `McpToolSpec`. From there, you pass the tools directly to your agent using `to_tool_list_async()`. This exposes all 12 financial endpoints as executable functions in your agentic loop.

Yes, you can use the `allowed_tools` filter when registering the tool spec. If you only want your agent to read data, you can restrict its access to `list_banks` and `get_bill` while blocking disbursement tools.

Transaction records from `list_payments` and bank details from `validate_bank_account` are processed strictly in-memory during index generation. No financial credentials or customer bank account numbers are cached on external servers or used for model training.

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