Bank data in your IDE
Add the BankSync MCP server to Tabnine and build finance features with your real bank data in context.
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 Tabnine 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 mcp_servers.json. The key header goes under requestInit.headers.
.tabnine/mcp_servers.json
{ "mcpServers": { "banksync": { "url": "https://mcp.banksync.io", "requestInit": { "headers": { "X-API-Key": "bsk_your_key_here" } } } } } - 03
Code with your data
Ask Tabnine’s chat for a feature and it reads the rows it needs.
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.
- Finance code completion
- Get AI code completions informed by real bank data schemas and transaction structures for accurate finance development.
- Type generation
- Generate TypeScript interfaces and type definitions based on actual bank data structures from 12,000+ institutions.
- API client development
- Build typed API clients for bank data endpoints with Tabnine suggesting accurate code based on real schemas.
- Enterprise finance tools
- Use Tabnine's enterprise features with your own BankSync data to build internal finance tools.
- Test data generation
- Create realistic test fixtures and mock data based on actual transaction patterns from connected bank accounts.
- Code documentation
- Generate accurate code documentation with Tabnine understanding the financial data structures in your codebase.
Change assistants. Keep your data.
What Tabnine 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
- ~/.tabnine/mcp_servers.json globally, or .tabnine/mcp_servers.json in a project.
- 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 Tabnine to BankSync?
Generate a BankSync API key, then add the BankSync MCP server configuration in your Tabnine settings. Tabnine will discover 227 financial data tools for AI-assisted finance development.
Does Tabnine support MCP servers?
Yes. Tabnine supports MCP through its configuration settings. You can add BankSync as an MCP server and use Tabnine AI to generate code with real financial data context.
Can Tabnine generate code using bank data schemas?
Yes. With BankSync MCP connected, Tabnine can reference real bank data schemas, transaction structures, and account types to generate accurate type definitions, API clients, and data models.
Is Tabnine with BankSync enterprise-ready?
Yes. Tabnine's enterprise features combined with BankSync's scoped API keys and granular permissions make it suitable for enterprise finance development environments.