BankSync MCP Server

BankSync MCP Server

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

Category
访问服务器

README

BankSync MCP Server

npm version PyPI version License: MIT smithery badge Install with NPX in VS Code

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

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

<!-- mcp-name: io.banksync/mcp -->

<p> <a href="https://banksync.io/product/mcp">Website</a> · <a href="https://banksync.io/developers">Docs</a> · <a href="https://banksync.io/developers/mcp-setup">Setup Guides</a> · <a href="#quick-start">Quick Start</a> · <a href="docs/TOOLS.md">Tools Reference</a> </p>


Quick Start

Get your API key at banksync.io/developers. BankSync runs as a remote MCP server — no install required:

URL:       https://mcp.banksync.io
Transport: Streamable HTTP
Header:    X-API-Key: your-key

Setup

<details> <summary><strong>Claude Desktop</strong></summary>

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

{
  "mcpServers": {
    "banksync": {
      "type": "http",
      "url": "https://mcp.banksync.io",
      "headers": {
        "X-API-Key": "your-key"
      }
    }
  }
}

</details>

<details> <summary><strong>Claude Code</strong></summary>

claude mcp add --transport http banksync https://mcp.banksync.io \
  --header "X-API-Key: your-key"

</details>

<details> <summary><strong>Cursor</strong></summary>

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "banksync": {
      "url": "https://mcp.banksync.io",
      "headers": {
        "X-API-Key": "your-key"
      }
    }
  }
}

</details>

<details> <summary><strong>VS Code (Copilot)</strong></summary>

Add to .vscode/mcp.json:

{
  "servers": {
    "banksync": {
      "type": "http",
      "url": "https://mcp.banksync.io",
      "headers": {
        "X-API-Key": "your-key"
      }
    }
  }
}

</details>

<details> <summary><strong>Windsurf</strong></summary>

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "banksync": {
      "serverUrl": "https://mcp.banksync.io",
      "headers": {
        "X-API-Key": "your-key"
      }
    }
  }
}

</details>

<details> <summary><strong>npm package (stdio fallback)</strong></summary>

For clients that don't support remote HTTP servers, use the npm package as a local bridge:

npx -y @banksync/mcp              # Node.js
pip install banksync-mcp && banksync-mcp  # Python

Set BANKSYNC_API_KEY=your-key as an environment variable. The package bridges stdio to https://mcp.banksync.io automatically.

Example config (any stdio client):

{
  "mcpServers": {
    "banksync": {
      "command": "npx",
      "args": ["-y", "@banksync/mcp"],
      "env": {
        "BANKSYNC_API_KEY": "your-key"
      }
    }
  }
}

</details>

Setup guides for all clients: banksync.io/developers/mcp-setup

What You Can Do

Ask your AI agent questions like:

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

Tools

28 tools across 7 categories. Full reference with parameters and examples: docs/TOOLS.md

Category Tools What They Do
Discovery get_data_type_schema, list_feed_sources Discover available fields and feed source types
Workspace list_workspaces, get_workspace, list_integrations, delete_integration Manage workspaces and connected destinations
Banks list_banks, get_bank, create_bank_link, connect_bank, delete_bank Connect and manage bank connections
Accounts list_accounts, get_account Fetch live account data from institutions
Financial Data get_transactions, get_balance, get_holdings, get_trades, get_loan Query transactions, balances, investments, loans
Feeds list_feeds, get_feed, create_feed, update_feed, validate_feed, delete_feed Build automated data pipelines
Jobs list_jobs, get_job, trigger_sync, cancel_job Run and monitor sync jobs

How It Works

AI Agent (Claude, ChatGPT, Cursor, ...)
    ↓ Streamable HTTP
mcp.banksync.io (Cloudflare Workers)
    ↓ Bank APIs
Plaid (US/UK/CA) · Basiq (AU/NZ)
    ↓ Sync
Notion · Google Sheets · Airtable

See docs/ARCHITECTURE.md for details.

Typical Workflow

1. list_workspaces          → find your workspace
2. list_banks               → see connected banks
3. list_accounts            → discover accounts
4. get_transactions         → fetch financial data
5. list_integrations        → find your Notion/Sheets connection
6. get_data_type_schema     → discover available field mappings
7. create_feed              → set up an automated pipeline
8. trigger_sync             → run it

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 structured data from forwarded emails
File upload Global AI-extracted data from PDFs, images, documents

Sync Destinations

Destination Capabilities
Notion Sync to Notion databases
Google Sheets Sync to spreadsheets (row or column direction)
Airtable Sync to Airtable tables

Security

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

See SECURITY.md for our security policy and vulnerability reporting.

Debugging

Use the MCP Inspector to test and debug the server:

BANKSYNC_API_KEY=your-key npx @modelcontextprotocol/inspector npx -y @banksync/mcp

Or connect the inspector directly to the remote server:

npx @modelcontextprotocol/inspector --url https://mcp.banksync.io --header "X-API-Key: your-key"

Documentation

Doc Description
docs/TOOLS.md Complete tools reference with parameters and examples
docs/ARCHITECTURE.md Architecture, transport, and deployment details
docs/AGENTS.md Guide for AI agents: best practices, prompt patterns, workflows
CLAUDE.md Context for AI coding assistants working on this repo
SECURITY.md Security policy and vulnerability reporting
banksync.io/developers Full API documentation
banksync.io/developers/mcp-setup Per-client setup guides

Privacy Policy

BankSync's privacy policy is available at banksync.io/privacy. BankSync never stores banking credentials — authentication is delegated to Plaid and Basiq. API keys are scoped per workspace and all data is encrypted in transit.

License

MIT — see LICENSE.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选