Build with bank data in VS Code
Add the BankSync MCP server to GitHub Copilot in VS Code and build with your real transactions, balances and investments in agent mode.
src/spend-by-category.ts
import { transactions } from './data' // From get_transactions, last 90 daysexport function spendByCategory() { const totals = new Map<string, number>() for (const tx of transactions) { if (tx.amount >= 0) continue const key = tx.category ?? 'Other' const prev = totals.get(key) ?? 0 totals.set(key, prev - tx.amount) } return [...totals].sort(byAmount)}
Agent
Connect VS Code in three steps.
- 01
Create a scoped key
Connect your banks in BankSync, then create an API key with read scopes under Developers.
New API key
NameMCP clientScopesbanks:readfeeds:readKeybsk_••••••••3f9a - 02
Add the server
Add BankSync to .vscode/mcp.json under servers (not mcpServers).
.vscode/mcp.json
{ "servers": { "banksync": { "type": "http", "url": "https://mcp.banksync.io", "headers": { "X-API-Key": "bsk_your_key_here" } } } } - 03
Use agent mode
Open Copilot Chat, switch to agent mode and build with your real data.
Pull the last 90 days of transactions and write a spend-by-category helper with a test.
get_transactions · 412 rows · Business Checking ••4021
Done. spendByCategory() is in src/, and the test uses 20 real rows as fixtures. Software is the top category at $4,212.
What you can build.
- Personal finance tooling
- Build your own finance scripts and internal tools with real transaction data context from your connected accounts.
- Financial data exploration
- Ask Copilot to query balances, transactions, and investments through natural language, no API docs needed.
- Code generation with schemas
- Generate type-safe code that matches actual bank data structures, account types, and transaction fields.
- Test data generation
- Create realistic test fixtures and mock data based on real transaction patterns from your bank accounts.
- API client development
- Let Copilot generate API client code with accurate type definitions from BankSync's MCP endpoints.
- Interactive dashboards
- Build financial dashboards and visualizations with MCP Apps support for rich interactive UI in Copilot Chat.
Change assistants. Keep your data.
What VS Code 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
- .vscode/mcp.json in the workspace, or your user settings. Needs the GitHub Copilot extension.
- 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 add BankSync MCP to GitHub Copilot in VS Code?
Generate a BankSync API key, then add the MCP server configuration to your .vscode/mcp.json file. The BankSync tools will be available in Copilot's agent mode.
Does GitHub Copilot support remote MCP servers like BankSync?
Yes. GitHub Copilot in VS Code supports MCP servers in agent mode, including remote servers like BankSync that connect via HTTP-based transports.
What version of VS Code do I need for MCP support?
You need VS Code 1.99 or later and an active GitHub Copilot subscription. Agent mode with MCP tool support is built into the Copilot Chat panel.
What can I build with GitHub Copilot and BankSync?
Build finance tools with live bank data context, generate code that works with real transaction schemas, create interactive financial dashboards, and automate data pipelines, all with AI assistance in VS Code.