Bank data in your IDE
Add the BankSync MCP server to Sourcegraph Cody and combine code intelligence with your real transactions, balances and investments.
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 Cody 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 under cody.mcpServers in your editor settings, or from Cody’s MCP Settings.
settings.json
"cody.mcpServers": { "banksync": { "command": "npx", "args": ["-y", "@banksync/mcp"], "env": { "BANKSYNC_API_KEY": "bsk_your_key_here" } } } - 03
Code with your data
Ask Cody 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.
- Codebase + bank data queries
- Ask Cody questions that combine codebase context with live bank data for comprehensive finance development.
- Financial code generation
- Generate code with real bank data schemas, using Cody code intelligence for accurate type definitions.
- API client development
- Build typed API clients for bank data endpoints with Cody understanding both your codebase and data structures.
- Code review with data context
- Review finance code with Cody having access to actual bank data structures for accurate suggestions.
- Test fixture generation
- Create test fixtures based on real transaction patterns, with Cody understanding your existing test patterns.
- Documentation generation
- Generate accurate API documentation with Cody referencing both your code and live bank data schemas.
Change assistants. Keep your data.
What Cody 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, passed to the @banksync/mcp bridge as BANKSYNC_API_KEY.
- Config
- VS Code settings.json or JetBrains cody_settings.json, under cody.mcpServers.
- 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 Sourcegraph Cody to BankSync?
Generate a BankSync API key, then add the BankSync MCP server configuration in your Cody settings. Cody will discover 227 financial data tools for use alongside its code intelligence features.
Can Cody search my codebase and bank data together?
Yes. Sourcegraph Cody combines its code intelligence (codebase search, context awareness) with BankSync's financial data tools. This means you can ask Cody questions that span both your codebase and bank data.
What financial data can Cody access?
Cody can access transactions, account balances, investment holdings, trades, and loan data from 12,000+ banks through the BankSync MCP server.
Does Cody work with BankSync in VS Code?
Yes. Sourcegraph Cody works as a VS Code extension and supports MCP servers. You can use BankSync MCP tools directly within VS Code through the Cody chat interface.