Connect BankSync to Python SDK

Build a custom MCP client in Python using the official MCP SDK with BankSync as the data source.

See the Python SDK MCP docs for more detail.

Prerequisites

  • A BankSync account with at least one connected bank
  • An API key with all permission scopes (created from Workspace → Developers)

Install the SDK

Install the official Model Context Protocol SDK:

Install
pip install mcp

Connect to BankSync

Point the client at the BankSync MCP server, replacing the placeholder with your API key:

Python SDK client
from mcp import ClientSession
from mcp.client.streamable_http import streamablehttp_client
async with streamablehttp_client(
"https://mcp.banksync.io",
headers={"X-API-Key": "bsk_your_api_key_here"}
) as (read, write, _):
async with ClientSession(read, write) as session:
await session.initialize()
tools = await session.list_tools()
Server URL. BankSync’s MCP server is at https://mcp.banksync.io over Streamable HTTP, authenticated with your X-API-Key.

Verify your connection

Restart your client and try these prompts to confirm the connection works:

List my workspaces
What banks do I have connected?
What’s my checking account balance?

Troubleshooting

“No tools available” or the MCP server is not listed

  • Make sure you restarted your AI client after editing the config file.
  • Verify the JSON/YAML is valid (no trailing commas, correct brackets).
  • Check 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  • Confirm the key starts with bsk_ and has not been revoked.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 passed in the X-API-Key header.
  • Check for stray whitespace or newlines around the key value.

Connection timeout or the client lacks remote HTTP support

  • The server uses Streamable HTTP. Allow outbound HTTPS to mcp.banksync.io.
  • If your client only supports local servers, use the npm bridge: npx -y @banksync/mcp.

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.

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 but your client does not, the issue is your client configuration.

Frequently asked questions

What is the official MCP Python SDK?

The official MCP Python SDK is the "mcp" pip package. It provides ClientSession and streamablehttp_client for connecting to MCP servers like BankSync using asyncio.

What Python version is required for the MCP SDK?

The MCP Python SDK requires Python 3.10 or later. It uses async/await syntax and the asyncio module for non-blocking MCP communication.

How do I authenticate with BankSync from Python?

Pass your BankSync API key in the headers parameter of streamablehttp_client() as {"X-API-Key": "bsk_your_api_key_here"}.