OpenOcean MCP
Enables interaction with decentralized exchanges (DEXs) through OpenOcean, allowing users to get swap quotes, execute token swaps, check gas prices, and query transaction information across multiple blockchain networks.
README
OPENOCEAN-MCP: Model Context Protocol Server for Decentralized Exchanges
This project implements a Model Context Protocol (MCP) server to interact with decentralized exchanges (DEXs). It allows MCP-compatible clients (like AI assistants, IDE extensions, or custom applications) to access functionalities such as getting quotes for swaps and executing swaps.
This server is built using TypeScript and fastmcp.
Features (MCP Tools)
The server exposes the following tools that MCP clients can utilize:
CHAIN_LIST: Fetch chain list.- Parameters:
GAS_PRICE: Fetch gas price.- Parameters:
chain(string)
- Parameters:
QUOTE: Fetch a quote for a swap.- Parameters:
chain(string),inTokenAddress(string),outTokenAddress(string),amount(string),slippage(string)
- Parameters:
SWAP: Building swap transaction.- Parameters:
chain(string),inTokenAddress(string),outTokenAddress(string),amount(string),slippage(string),account(string)
- Parameters:
GET_TRANSACTION: Fetch transaction info.- Parameters:
chain(string),hash(string)
- Parameters:
TOKEN_LIST: Fetch token list.- Parameters:
chain(string)
- Parameters:
DEX_LIST: Fetch dex list.- Parameters:
chain(string)
- Parameters:
Parameter breakdown
chain: The chain code of the DEX.inTokenAddress: The token you want to sell.outTokenAddress: The token you want to buy.amount: Token amount with decimals. For example, if 1 USDT is input, use 1000000 (1 USDT * 10^6).slippage: Define the acceptable slippage level by inputting a percentage value within the range of 0.05 to 50. 1% slippage set as 1.account: user's wallet address.hash: Hash from the OpenOcean contract on the blockchain.
Prerequisites
- Node.js (v18 or newer recommended)
- pnpm (See https://pnpm.io/installation)
Installation
There are a few ways to use openocean-mcp:
1. Using pnpm dlx (Recommended for most MCP client setups):
You can run the server directly using pnpm dlx without needing a global installation. This is often the easiest way to integrate with MCP clients. See the "Running the Server with an MCP Client" section for examples.
(pnpm dlx is pnpm's equivalent of npx)
2. Global Installation from npm (via pnpm):
Install the package globally to make the openocean-mcp command available system-wide:
pnpm add -g openocean-mcp
3. Building from Source (for development or custom modifications):
-
Clone the repository:
git clone https://github.com/openocean-finance/openocean-mcp.git cd openocean-mcp -
Install dependencies:
pnpm install -
Build the server: This compiles the TypeScript code to JavaScript in the
distdirectory.pnpm run buildThe
preparescript also runspnpm run build, so dependencies are built upon installation if you clone and runpnpm install.
Configuration (Environment Variables)
This MCP server may require certain environment variables to be set by the MCP client that runs it. These are typically configured in the client's MCP server definition (e.g., in a mcp.json file for Cursor, or similar for other clients).
- Any necessary environment variables for wallet providers or API keys.
Running the Server with an MCP Client
MCP clients (like AI assistants, IDE extensions, etc.) will run this server as a background process. You need to configure the client to tell it how to start your server.
Below is an example configuration snippet that an MCP client might use (e.g., in a mcp_servers.json or similar configuration file). This example shows how to run the server using the published npm package via pnpm dlx.
{
"mcpServers": {
"openocean-mcp-server": {
"command": "pnpm",
"args": ["dlx", "openocean-mcp"]
}
}
}
Alternative if Globally Installed:
If you have installed openocean-mcp globally (pnpm add -g openocean-mcp), you can simplify the command and args:
{
"mcpServers": {
"openocean-mcp-server": {
"command": "openocean-mcp",
"args": []
}
}
}
command: The executable to run.- For
pnpm dlx:"pnpm"(with"dlx"as the first arg) - For global install:
"openocean-mcp"
- For
args: An array of arguments to pass to the command.- For
pnpm dlx:["dlx", "openocean-mcp"] - For global install:
[]
- For
env: An object containing environment variables to be set when the server process starts. This is where you provide any necessary environment variables.workingDirectory: Generally not required when using the published package viapnpm dlxor a global install, as the package should handle its own paths correctly. If you were running from source (node dist/index.js), then settingworkingDirectoryto the project root would be important.
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.