How to Use the Column MCP in LlamaIndex

Q: How do I load Column bank statements into a LlamaIndex vector store?

Use the MCP client to fetch the data via columngetstatement. LlamaIndex then parses the response into document nodes for your vector index.

Q: How does the LlamaIndex MCP integration handle Column sandbox testing?

Run columnsimulateach to create mock inbound payments. The MCP client retrieves these test events, indexing them so you can test your search queries.

Q: Does this MCP tool suite allow querying live balances?

Yes, your agent calls columngetbalance to get real-time settled funds. This value is injected directly into your prompt context.

Index live bank statements and transaction feeds into your LlamaIndex knowledge base using the Column 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 Column MCP to LlamaIndex

Create your Vinkius account to connect Column 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 Column with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index bank statements directly into LlamaIndex vector stores

Convert raw bank records into searchable context using `column_get_statement`. This turns cold PDF bank records into active context for your RAG pipeline. Instead of manual lookups, you query your index about specific payouts. The LlamaIndex agent pulls the exact document chunk, matching it with real-time balance checks from `column_get_balance`.

Semantic search over active KYC entity profiles

Sync your customer registry with a local vector index using `column_list_entities`. When your agent needs to check if a business is approved, it searches the vector store instead of hitting the live API repeatedly. This setup speeds up decision-making for high-volume onboarding. Your LlamaIndex pipeline matches incoming applications against existing KYC profiles instantly.

Context-aware ACH tracking and auditing

Feed historical transfer data from `column_list_transfers` straight into your query engine. The agent analyzes past ACH transactions to answer complex natural language questions about cash flow trends. It pairs these past logs with live routing lookups from `column_get_bank_account`. That's how your financial agent gets a complete, grounded view of your banking operations.

Setup guide

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

Use the MCP client to fetch the data via `column_get_statement`. LlamaIndex then parses the response into document nodes for your vector index.

Yes. The agent queries your indexed KYC profiles, then calls `column_create_bank_account` once it confirms the entity exists in Column.

Run `column_simulate_ach` to create mock inbound payments. The MCP client retrieves these test events, indexing them so you can test your search queries.

Yes, your agent calls `column_get_balance` to get real-time settled funds. This value is injected directly into your prompt context.

Your entity profiles, ACH records, and routing information are processed in memory and never stored by Vinkius. Your vector database holds the embeddings, while Column holds the actual banking records.

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