About Oanda MCP Server
Oanda MCP Server exposes Oanda trading and market-data operations through a REST API. It is for clients that need to retrieve account and price information or manage orders and positions.
Key features
- 01Retrieve account information
- 02View positions and pending orders
- 03Get current and historical prices
- 04Place market and limit orders
- 05Cancel orders and close positions
Use cases
- 01Review account and open-position information
- 02Check current or historical instrument prices
- 03Place or cancel Oanda orders
- 04Close an instrument position
MCP support
The REST API server is compatible with Model Context Protocol (MCP), making its Oanda operations available to MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEOanda MCP Server
A REST API server for Oanda trading operations, deployed on Railway and compatible with Model Context Protocol (MCP).
Features
- Account information retrieval
- Position management
- Order placement (market and limit orders)
- Current price data
- Historical data
- Order cancellation
API Endpoints
GET /- Health checkGET /account- Get account informationGET /positions- Get current positionsGET /orders- Get pending ordersGET /price/{instrument}- Get current price for instrumentGET /historical/{instrument}- Get historical dataPOST /order/market- Place market orderPOST /order/limit- Place limit orderDELETE /order/{order_id}- Cancel orderPOST /position/close/{instrument}- Close position
Environment Variables
OANDA_API_KEY- Your Oanda API keyOANDA_ACCOUNT_ID- Your Oanda account IDOANDA_ENVIRONMENT- 'practice' or 'live'PORT- Server port (set automatically by Railway)
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.