Skip to main content

BankSync MCP server — connect AI agents to bank accounts, transactions, balances, and investment data

Project description

banksync-mcp

PyPI version Python License: MIT

Connect AI agents to real bank accounts — transactions, balances, investments, and loans — across 15,000+ financial institutions.

banksync-mcp is a Model Context Protocol server with 28 tools that gives Claude, ChatGPT, Cursor, VS Code, and other AI agents secure access to your financial data. Sync to Notion, Google Sheets, and Airtable — all through conversation.

Installation

pip install banksync-mcp

Or with uv:

uv pip install banksync-mcp

Requires Python 3.10+ and a BANKSYNC_API_KEY environment variable. Get your API key at banksync.io/developers.

Quick Start

export BANKSYNC_API_KEY=your-key
banksync-mcp

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "banksync": {
      "command": "banksync-mcp",
      "env": {
        "BANKSYNC_API_KEY": "your-key"
      }
    }
  }
}

Claude Code

claude mcp add banksync -e BANKSYNC_API_KEY=your-key -- banksync-mcp

Cursor / VS Code / Windsurf

{
  "mcpServers": {
    "banksync": {
      "command": "banksync-mcp",
      "env": {
        "BANKSYNC_API_KEY": "your-key"
      }
    }
  }
}

For clients that support remote MCP servers, you can connect directly to https://mcp.banksync.io with an X-API-Key header instead. See setup guides.

Usage

Ask your AI agent:

  • "What were my biggest expenses last month?"
  • "How much do I have across all my accounts?"
  • "Sync my transactions to Notion every week"
  • "Show my investment portfolio performance"
  • "What's my outstanding loan balance?"

Tools

28 tools across 7 categories:

Category Tools
Discovery get_data_type_schema, list_feed_sources
Workspace list_workspaces, get_workspace, list_integrations, delete_integration
Banks list_banks, get_bank, create_bank_link, connect_bank, delete_bank
Accounts list_accounts, get_account
Financial Data get_transactions, get_balance, get_holdings, get_trades, get_loan
Feeds list_feeds, get_feed, create_feed, update_feed, validate_feed, delete_feed
Jobs list_jobs, get_job, trigger_sync, cancel_job

Full reference: Tools Documentation

Data Sources

Provider Coverage Data Types
Plaid US, UK, Canada — 12,000+ institutions Transactions, balances, investments, loans
Basiq Australia, New Zealand — 3,000+ institutions Transactions, balances
Email extraction Global AI-extracted data from forwarded emails
File upload Global AI-extracted data from PDFs, images, documents

Sync Destinations

Notion, Google Sheets, and Airtable — with automated scheduling (daily, weekly, monthly).

How It Works

This package is a thin stdio-to-HTTP bridge. It validates your API key and forwards MCP messages to https://mcp.banksync.io using the mcp SDK's async streamable HTTP transport. No financial data is stored locally.

Security

  • API key authentication scoped per workspace
  • All data encrypted in transit (TLS)
  • Role-based permissions (owner/admin/editor/viewer)
  • Banking credentials delegated to Plaid/Basiq — never stored by BankSync
  • Stateless MCP transport — no session data persisted

Documentation

License

MIT — see LICENSE.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

banksync_mcp-1.0.1.tar.gz (56.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

banksync_mcp-1.0.1-py3-none-any.whl (4.3 kB view details)

Uploaded Python 3

File details

Details for the file banksync_mcp-1.0.1.tar.gz.

File metadata

  • Download URL: banksync_mcp-1.0.1.tar.gz
  • Upload date:
  • Size: 56.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for banksync_mcp-1.0.1.tar.gz
Algorithm Hash digest
SHA256 2d3b150aa49e1a5e5b03203dbce0d573aee4d603e04f7de49ae0822ad5131193
MD5 f9afe7e566b8ba1b081311f640efe84c
BLAKE2b-256 5ba938d05e8ffe84f24b8fda83d97efbf87c20ae951d4b73153b5e3eab8e1b9c

See more details on using hashes here.

Provenance

The following attestation bundles were made for banksync_mcp-1.0.1.tar.gz:

Publisher: publish-pypi.yml on banksynchq/banksync-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file banksync_mcp-1.0.1-py3-none-any.whl.

File metadata

  • Download URL: banksync_mcp-1.0.1-py3-none-any.whl
  • Upload date:
  • Size: 4.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for banksync_mcp-1.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 0e5164dc554fd8283ff9a13f7f1e55ddd736867a58d39a6fdb6896d1d0e9f977
MD5 5200185cbf48d9c59960ba096d33b5f8
BLAKE2b-256 d8b14526d8dfd4f0791acc25c7401f3d9fad730477d3d868ea167e48801ba55a

See more details on using hashes here.

Provenance

The following attestation bundles were made for banksync_mcp-1.0.1-py3-none-any.whl:

Publisher: publish-pypi.yml on banksynchq/banksync-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page