Connect BankSync to Gemini
Connecting custom MCP servers to the Gemini web app (gemini.google.com) is currently available only to Google Cloud Enterprise customers on an allowlist basis. For most users, the best way to use BankSync with Gemini is via Gemini CLI, which has full MCP support.
Prerequisites
- A BankSync account with at least one connected bank
- An API key with all permission scopes (created from Workspace menu → Developers)
Enterprise only: Custom MCP connectors in the Gemini web experience (Google Cloud AI Enterprise) require contacting your Google account team to be added to the allowlist.
Recommended: Use Gemini CLI
Gemini CLI is Google's terminal AI coding agent with full MCP support — available to all users. See the Gemini CLI setup guide to get started.
Google Cloud AI Enterprise Setup
If you have access to Google Cloud AI Enterprise with custom MCP connectors enabled, configure BankSync through the Google Cloud console:
- MCP Server URL:
https://mcp.banksync.io - Authentication: API key header (
X-API-Key) - Contact your Google account team for access and configuration steps
Verify Your Connection
After configuring your client, restart it and try these prompts to verify the connection is working:
“List my workspaces”
“What banks do I have connected?”
“What’s my checking account balance?”
Troubleshooting
“No tools available” or MCP server not listed
- Make sure you restarted your AI client after editing the configuration file.
- Verify the JSON is valid (no trailing commas, correct brackets).
- Check that the URL is exactly
https://mcp.banksync.io.
“Authentication failed” or “Invalid API key”
- Confirm the key starts with
bsk_and has not been revoked. - Ensure the key is in the
headersobject underX-API-Key. - Check for accidental whitespace or newlines around the key value.
Tools are listed but return errors
- Verify your API key has the required scopes. For full access, select all scopes when creating the key.
- Make sure you have at least one bank connected in the BankSync app.
- Check that you are passing the correct workspace ID when prompted.
Connection timeout or network errors
- The MCP server uses Streamable HTTP transport. Ensure your network or proxy allows outbound HTTPS connections.
- If using a VPN or firewall, allow connections to
mcp.banksync.io. - Try the connection from a different network to rule out local issues.
- If your client does not support remote HTTP servers, use the npm package instead:
npx -y @banksync/mcp
Debugging with MCP Inspector
- Use the MCP Inspector to test the connection independently of your AI client.
- Run:
npx @modelcontextprotocol/inspector --url https://mcp.banksync.io --header "X-API-Key: bsk_your_key" - If the Inspector connects successfully but your client does not, the issue is with your client configuration.