Wise MCP Server
Enables access to Wise API functionality for managing recipients and sending money transfers. Supports listing recipients, creating new recipients, validating account details, and executing money transfers with authentication handling.
README
Wise MCP Server
A MCP (Machine Communication Protocol) server that serves as a gateway for the Wise API, providing simplified access to Wise's recipient functionality.
Features
- List all recipients from your Wise account via a simple MCP resource
- Automatically handles authentication and profile selection
- Uses the Wise Sandbox API for development and testing
- Available as a Docker image for easy integration
Requirements
- Python 3.12 or higher (only if installing directly)
uvpackage manager (only if installing directly)- Wise API token
- Docker (if using Docker image)
Get an API token
https://wise.com/your-account/integrations-and-tools/api-tokens
Create a new token here.
Installation
Option 1: Direct Installation
-
Clone this repository:
git clone https://github.com/sergeiledvanov/mcp-wise cd wise-mcp -
Set up the environment:
cp .env.example .env # Edit .env to add your Wise API token -
Install dependencies with
uv:uv venv uv pip install -e .
Option 2: Using Docker
You can build a Docker image:
docker build -t mcp-wise .
And add to Claude Code by adding it to your .mcp.json
{
"mcpServers": {
"mcp-wise": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"--init",
"-e", "WISE_API_TOKEN=your_api_token_here",
"-e", "WISE_IS_SANDBOX=true",
"mcp-wise:latest"
]
}
}
}
Make sure to replace your_api_token_here with your actual Wise API token.
Make sure to also update your .mcp.json file to match your selected mode. We provide template files that you can use:
-
For stdio mode (default):
cp .mcp.json.stdio .mcp.json -
For HTTP mode:
cp .mcp.json.http .mcp.json
These template files contain the appropriate configuration for each mode.
Available MCP Resources
The server provides the following MCP resources:
list_recipients
Returns a list of all recipients from your Wise account.
Parameters:
profile_type: The type of profile to list recipients for. One of [personal, business]. Default: "personal"currency: Optional. Filter recipients by currency code (e.g., 'EUR', 'USD')
get_recipient_requirements
Fetches recipient requirements for creating a new recipient. If account details are provided, validates the account details against the requirements.
Parameters:
source_currency: The source currency code (e.g., 'USD')target_currency: The target currency code (e.g., 'EUR')source_amount: The amount in the source currencyprofile_type: The type of profile to use. One of [personal, business]. Default: "personal"account: Optional. The recipient account details to validate against requirements. If not provided, returns the initial account requirements.
create_recipient
Creates a new recipient with the provided account details.
Parameters:
profile_type: The type of profile to use. One of [personal, business]. Default: "personal"account: The recipient account details compliant with Wise API requirements. This should include:accountHolderName: Name of the account holdercurrency: Target currency code (e.g., 'EUR')type: Account type (e.g., 'iban', 'sort_code', etc.)details: Object containing account-specific details (varies by currency and country)
send_money
Sends money to a recipient using the Wise API.
Parameters:
profile_type: The type of profile to use (personal or business)source_currency: Source currency code (e.g., 'USD')source_amount: Amount in source currency to sendrecipient_id: The ID of the recipient to send money topayment_reference: Optional. Reference message for the transfer (defaults to "money")source_of_funds: Optional. Source of the funds (e.g., "salary", "savings")
Configuration
Configuration is done via environment variables, which can be set in the .env file:
WISE_API_TOKEN: Your Wise API token (required)WISE_IS_SANDBOX: Set to true to use the Wise Sandbox API (default: false)MODE: MCP Server transport mode, either "http" or "stdio" (default: stdio)
Development
Project Structure
wise-mcp/
├── .env # Environment variables (not in git)
├── .env.example # Example environment variables
├── pyproject.toml # Project dependencies and configuration
├── README.md # This file
└── src/ # Source code
├── main.py # Entry point
└── wise_mcp/ # Main package
├── api/ # API clients
│ └── wise_client.py # Wise API client
├── resources/ # MCP resources
│ └── recipients.py # Recipients resource
└── app.py # MCP application setup
Adding New Features
To add new features:
- Add new API client methods in
src/wise_mcp/api/wise_client.py - Create new resources in
src/wise_mcp/resources/ - Import and register the new resources in
src/wise_mcp/app.py
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
MIT
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.
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.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.
E2B
Using MCP to run code via e2b.