Tool-Plaid
Enables interaction with Plaid's financial data API to sync bank transactions and retrieve account balances with secure encrypted token storage.
README
Tool-Plaid: MCP Server for Plaid
MCP (Model Context Protocol) server tool that exposes two tools for interacting with Plaid's financial data API:
sync_transactions- Retrieve and sync transaction dataget_balance- Get account balances
Installation
Development Installation
# Clone the repository
git clone https://github.com/reilly3000/tool-plaid.git
cd tool-plaid
# Install in development mode
pip install -e .
# Or with uv (recommended)
uv pip install -e .
Production Installation
pip install tool-plaid
# or with uv
uv pip install tool-plaid
Configuration
Environment Variables
Create a .env file in the project root or set environment variables:
# Plaid Configuration
PLAID_ENV=sandbox|production
PLAID_CLIENT_ID=<your_client_id>
PLAID_SECRET=<your_secret>
# Security
ENCRYPTION_KEY=<your_32_byte_encryption_key>
# Storage
STORAGE_MODE=file|postgres
DATABASE_URL=postgresql://user:pass@host:port/dbname # required if STORAGE_MODE=postgres
# MCP Server
MCP_TRANSPORT=stdio|streamable-http
MCP_PORT=8000
# Caching (optional)
BALANCE_CACHE_TTL=300 # seconds, default: 300 (5 minutes)
Example .env File
# Sandbox Environment
PLAID_ENV=sandbox
PLAID_CLIENT_ID=62eacf714206f30013d6e722
PLAID_SECRET=6f85aa5808d484246313470945c515
# Generate a random 32-byte key
ENCRYPTION_KEY=$(python -c "import secrets; print(secrets.token_urlsafe(32))")
# Start with file storage
STORAGE_MODE=file
Usage
Running the Server
Local Development (STDIO)
# Set environment
export PLAID_ENV=sandbox
export PLAID_CLIENT_ID=<your_client_id>
export PLAID_SECRET=<your_secret>
export STORAGE_MODE=file
# Run with uv
uv run plaid-tool
# Or directly
python -m tool_plaid
Production (Streamable HTTP)
export PLAID_ENV=production
export DATABASE_URL=postgresql://...
export STORAGE_MODE=postgres
export MCP_TRANSPORT=streamable-http
# Run HTTP server
plaid-tool
Configuration with Claude Desktop
Add this to your MCP configuration file (e.g., claude_desktop_config.json):
{
"mcpServers": {
"plaid": {
"command": "plaid-tool",
"env": {
"PLAID_ENV": "sandbox"
}
}
}
}
Tools
sync_transactions
Sync transactions from Plaid using cursor-based incremental updates.
Parameters:
item_id(required): Plaid item identifierforce_refresh(optional, default=False): Trigger Plaid refreshdays_requested(optional, default=90, range 1-730): Days of history
Returns:
{
"added": [
{
"transaction_id": "string",
"account_id": "string",
"amount": 100.50,
"date": "2025-01-15",
"merchant_name": "Merchant Name",
"category": "Food and Drink",
"pending": false
}
],
"modified": [...],
"removed": ["transaction_id_1", "transaction_id_2"],
"next_cursor": "cursor_string",
"has_more": false,
"item_status": "HISTORICAL_UPDATE_COMPLETE",
"summary": "Added 10, modified 2, removed 1 transactions"
}
get_balance
Get account balances with intelligent caching.
Parameters:
item_id(required): Plaid item identifieraccount_ids(optional, default=None): Filter specific accountsforce_refresh(optional, default=False): Bypass cache
Returns:
{
"balances": [
{
"account_id": "string",
"name": "Plaid Checking",
"mask": "0000",
"type": "depository",
"available": 1000.00,
"current": 1250.00,
"iso_currency_code": "USD"
}
],
"cached": true,
"timestamp": "2025-01-15T10:30:00Z"
}
Architecture
Storage Modes
File Storage (Development)
- JSONL files for transactions
- Simple key-value cursor tracking
- Text-based balance snapshots
- Directory:
data/items/{item_id}/
PostgreSQL (Production)
- Async PostgreSQL with asyncpgres
- Tables:
access_tokens,transactions,balances,cursors - Connection pooling
- Migrations via alembic
Security
- AES-256 encryption for access tokens at rest
- Encryption key from environment variable
- No logging of sensitive data (tokens, raw responses)
- Audit logging without sensitive data
Development
Running Tests
# Install dev dependencies
pip install -e ".[dev]"
# Run tests
pytest
# Run with coverage
pytest --cov=tool_plaid --cov-report=html
# Run integration tests (requires Sandbox credentials)
pytest tests/integration/ -m integration
Code Quality
# Format code
black tool_plaid
# Lint
ruff check tool_plaid
# Type check
mypy tool_plaid
License
MIT
Support
For issues and questions, please open an issue on GitHub.
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。