Bank data with local AI

Add the BankSync MCP server to LM Studio and ask about your transactions, balances and investments with a model running on your machine.

LM StudioBankSync MCP
A local model in LM Studio reading Total Checking through BankSync.

Connect LM Studio in three steps.

  1. 01

    Create a scoped key

    Connect your banks in BankSync, then create an API key with read scopes under Developers.

    New API key

    NameMCP client
    Scopesbanks:readfeeds:read
    Keybsk_••••••••3f9a
  2. 02

    Add the server

    In LM Studio, open the Program tab, edit mcp.json and add the BankSync entry.

    mcp.json

    {
      "mcpServers": {
        "banksync": {
          "url": "https://mcp.banksync.io",
          "headers": {
            "X-API-Key": "bsk_your_key_here"
          }
        }
      }
    }
  3. 03

    Ask your local model

    Load a model with tool calling and ask about your money.

    What did we spend on groceries this month, and is it more than September?

    get_transactions · 23 rows · Total Checking ••7731

    $642.18 across 23 trips, $58 more than September. Whole Foods is most of it.

What you can ask.

Private financial analysis
Analyze your bank data with locally-running AI models, your financial queries never leave your machine.
Local spending reports
Generate spending breakdowns and financial reports using local models with live bank data access.
Offline-first finance
Run financial analysis workflows that work even when cloud AI services are unavailable.
Model comparison
Compare how different local models handle financial queries using real bank data from BankSync.
Custom financial agents
Build custom financial AI agents using local models with access to real transaction and balance data.
Budget planning
Create budget plans with local AI assistance analyzing your actual spending patterns.

What LM Studio gets.

Server
Remote and hosted at https://mcp.banksync.io over Streamable HTTP. Nothing to install.
Tools
227 documented tools: bank data, feeds and jobs, tables, dashboards, automations and enrichments. Tools reference
Sign-in
A scoped API key, sent in the X-API-Key header.
Config
LM Studio’s mcp.json, from the Program tab.
Access
Set by the scopes you grant. Read scopes keep the connection read-only; no tool can move money.
Rate limits
20 tool calls a minute on Standard, 40 on Professional, 60 on Business, shared across a workspace.
Banks
12,000+ institutions in the US, Canada, the UK, Europe and Australia, including Consumer Data Right connections.

Questions, answered.

How do I connect LM Studio to BankSync?

Generate a BankSync API key, then add the BankSync MCP server configuration in your LM Studio settings. Your local AI model will have access to 227 financial data tools.

Can I use local models with BankSync?

Yes. LM Studio runs models locally on your machine. With BankSync MCP connected, any local model can access bank transactions, balances, and investments, keeping your model inference private while accessing live financial data.

What models work best with BankSync in LM Studio?

Any model with tool-calling support works well with BankSync MCP in LM Studio. Models like Llama, Mistral, and Qwen with function-calling capabilities provide the best experience for financial data queries.

Is my data private when using LM Studio with BankSync?

LM Studio runs models locally, so your model inference stays on your machine. BankSync data is fetched over encrypted connections with scoped API keys. You get local AI privacy with cloud bank data access.

Private financial AI with local models