Give Goose access to your bank data
Add the BankSync MCP server to Goose and let Block’s open-source agent automate financial work with your real transactions and balances.
$goose sessionEvery Monday, write last week’s spending to a CSV in ~/reports.banksync · get_transactions 58 rows · Business Checking ••4021Wrote ~/reports/week-41.csv with 58 rows and added a Monday cron entry for the next ones.
Connect Goose 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 extension
Add BankSync as a streamable_http extension in Goose’s config.yaml, or through goose configure.
~/.config/goose/config.yaml
extensions: banksync: enabled: true name: BankSync type: streamable_http uri: https://mcp.banksync.io headers: X-API-Key: bsk_your_key_here - 03
Automate the work
Let Goose run commands, edit files and build workflows on your real data.
Every Monday, write last week’s spending to a CSV in ~/reports.
get_transactions · 58 rows · Business Checking ••4021
Wrote ~/reports/week-41.csv with 58 rows and added a Monday cron entry for the next ones.
What you can build.
- Financial automation
- Let Goose run commands and scripts that pull, transform, and analyze your bank data automatically.
- Data pipeline orchestration
- Orchestrate multi-step ETL workflows that sync bank transactions into databases, spreadsheets, or APIs.
- Spending analysis scripts
- Generate and execute scripts that categorize transactions, detect patterns, and produce spending reports.
- Budget tool development
- Build budgeting applications with Goose editing files, running tests, and iterating with live bank data.
- Multi-step financial workflows
- Chain together account lookups, balance checks, and transaction queries into complex agentic workflows.
- Cross-tool integration
- Combine BankSync MCP with other MCP servers in Goose to connect bank data with your entire dev toolchain.
Change assistants. Keep your data.
What Goose 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
- ~/.config/goose/config.yaml under extensions, or goose configure.
- 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 Goose?
Generate a BankSync API key, then add the MCP server configuration to your Goose config file. BankSync tools will be available through Goose's native MCP integration.
Does Goose support remote MCP servers like BankSync?
Yes. Goose has native MCP integration and supports remote server connections, enabling seamless integration with cloud-hosted MCP servers like BankSync.
What LLM providers does Goose work with?
Goose is model-agnostic and supports 25+ LLM providers. You can use BankSync MCP tools with any supported model, including OpenAI, Anthropic, and local models.
What can I automate with Goose and BankSync?
Automate financial data pipelines, generate spending analysis scripts, orchestrate multi-step banking workflows, build budget tools, and integrate bank data across your development toolchain, all through Goose's agentic capabilities.