---
title: "How to give Ollama access to your bank account"
description: "Ollama runs the model, not the tools. Put Hermes Agent or Open WebUI in front of it, add BankBridge, and a local model can read your bank. Read-only."
slug: "how-to-give-ollama-access-to-your-bank-account"
url: "https://bankbridge.money/guides/how-to-give-ollama-access-to-your-bank-account"
category: "how-to"
published: "2026-11-06"
updated: "2026-11-06"
---
# How to give Ollama access to your bank account

> Ollama runs models but can't call MCP tools by itself, so you put an agent in front of it: Hermes Agent in the terminal or Open WebUI in the browser. Point that agent at Ollama for the model and at BankBridge for your bank, with your bbk_ key. The conversation stays on your machine; bank reads go through BankBridge, which keeps no copy.

## How the pieces fit

Three parts: Ollama runs the model, an agent turns the model’s tool calls into MCP requests, and BankBridge answers those requests from your bank. Ollama never talks to BankBridge. The agent talks to both.

You need a BankBridge key first: sign up at [bankbridge.money/login](https://bankbridge.money/login), link a bank, and copy the `bbk_` key from your dashboard. To try the setup before you pay, use the key `bbk_demo`, which returns sample data.

## 1\. Run a model that calls tools

Pull a model with tool support and give the server a large context. Agents send a long list of tools with every request, and a short window cuts it off.

terminal

```
ollama pull qwen3:8b
OLLAMA_CONTEXT_LENGTH=65536 ollama serve
```

## 2\. Hermes Agent in front of Ollama

Hermes Agent reads both the model and the MCP servers from `~/.hermes/config.yaml`. Point the model at Ollama’s OpenAI-compatible endpoint and add BankBridge:

~/.hermes/config.yaml

```
model:
  provider: custom
  default: qwen3:8b
  base_url: http://127.0.0.1:11434/v1
  api_key: ollama
  context_length: 65536
  ollama_num_ctx: 65536
mcp_servers:
  bankbridge:
    url: "https://bankbridge.money/api/mcp"
    headers:
      Authorization: "Bearer bbk_your_api_key_here"
```

Hermes refuses models with less than 64,000 tokens of context, which is why both `context_length` and `ollama_num_ctx` are set. Check the connection with `hermes mcp test bankbridge` (it should report 12 tools), then ask:

terminal

```
hermes chat -q "List my bank accounts and balances"
```

With the demo key and qwen3:0.6b, Hermes called `mcp__bankbridge__list_accounts` and answered “The first account is Chase Total Checking.” Full steps: [Hermes Agent setup](https://bankbridge.money/docs/hermes).

## Or: Open WebUI in front of Ollama

Open WebUI is a chat window in your browser that uses Ollama for models. Add BankBridge as an MCP tool server in its admin settings, then turn it on in a chat. The steps are on the [Open WebUI setup page](https://bankbridge.money/docs/open-webui).

## What about LM Studio?

LM Studio doesn’t run behind Ollama. It downloads and runs its own models, so it replaces Ollama rather than sitting in front of it. If you want one app that runs the model and the tools, [LM Studio takes BankBridge in its mcp.json](https://bankbridge.money/docs/lm-studio).

## What stays on your machine

Your question, the model’s work and its answer stay on your machine. When the model calls a tool, the tool name and arguments go to BankBridge over HTTPS, BankBridge asks the bank-data provider, and the result comes back to your agent. BankBridge keeps no copy of balances or transactions. More on this in [agents you run yourself](https://bankbridge.money/local-agents).

## FAQ

### Can Ollama connect to an MCP server by itself?

No. Ollama serves models over an API. Tool calls come from the app talking to it, so the MCP server is configured in that app: Hermes Agent, Open WebUI, or another agent that supports MCP.

### Which Ollama model should I use?

One tagged for tools in the Ollama library, with as much context as your machine can hold. Small models miss tool calls more often. Our test used qwen3:0.6b and it called list_accounts correctly; a larger model handles multi-step questions better.

### Why does Hermes say the context window is too small?

Hermes Agent requires at least 64,000 tokens. Start Ollama with OLLAMA_CONTEXT_LENGTH=65536 and set model.ollama_num_ctx: 65536 in ~/.hermes/config.yaml.

### Does my bank data stay on my computer?

The conversation does. The numbers come from your bank through the bank-data provider and BankBridge over HTTPS, and BankBridge keeps no copy. Reading your bank needs an internet connection even when the model runs offline.

### What does it cost?

$5 a month per connected bank, or $50 a year. Ollama and the agents here are separate software you run yourself.