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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.