
LI.FI MCP Server
Enables AI assistants to interact with LI.FI's cross-chain infrastructure, providing access to blockchain networks, token data, bridges, and transaction services through a standardized protocol.
README
LI.FI MCP Server
A Model Context Protocol (MCP) server that provides comprehensive integration with the LI.FI API for cross-chain bridge and DEX aggregation services.
Overview
This MCP server enables AI assistants and applications to interact with LI.FI's cross-chain infrastructure through a standardized protocol. It provides access to blockchain network information, token data, bridging tools, transaction status tracking, and more.
Features
Available Tools
- Chain Information (
lifi_get_chains
) - Get information about all supported blockchain networks - Token Data (
lifi_get_tokens
) - Retrieve comprehensive token information across chains - Specific Token (
lifi_get_token
) - Get detailed information about a specific token - Bridge & Exchange Tools (
lifi_get_tools
) - List available bridges and exchanges - Chain Connections (
lifi_get_connections
) - Explore supported cross-chain connections - Gas Price Data (
lifi_get_gas_prices
) - Get current gas prices for specific chains - Gas Suggestions (
lifi_get_gas_suggestion
) - Get gas amount recommendations - Transaction Status (
lifi_get_transaction_status
) - Track cross-chain transfer status - Fee Withdrawal (
lifi_get_integrator_fee_withdrawal
) - Manage integrator fee withdrawals
Prerequisites
- Node.js (v16 or higher)
- npm or yarn
- LI.FI API key
Installation
- Clone the repository:
git clone <repository-url>
cd lifi-mcp-server
- Install dependencies:
npm install
- Obtain a LI.FI API key:
- Visit LI.FI Developer Portal to register and get your API key
- Keep your API key secure and ready for configuration
Configuration
The server requires the following configuration:
lifiApiKey
(required): Your LI.FI API key for authenticationdebug
(optional): Enable debug logging (default: false)
Development
Start the development server:
npm run dev
This will start the MCP server using Smithery CLI with hot reloading enabled.
Usage
With MCP-Compatible Applications
This server can be used with any application that supports the Model Context Protocol, such as:
- Claude Desktop
- MCP-enabled IDEs
- Custom MCP clients
Example Configuration
For Claude Desktop, add to your claude_desktop_config.json
:
{
"mcpServers": {
"lifi": {
"command": "node",
"args": ["path/to/lifi-mcp-server/dist/index.js"],
"env": {
"LIFI_API_KEY": "your-api-key-here"
}
}
}
}
Tool Examples
Get supported chains:
lifi_get_chains
Get tokens for specific chains:
lifi_get_tokens(chains: "1,137,42161")
Check transaction status:
lifi_get_transaction_status(txHash: "0x...")
Get gas prices:
lifi_get_gas_prices(chainId: "1")
API Reference
Chain Operations
lifi_get_chains(chainTypes?)
- List supported blockchain networks
Token Operations
lifi_get_tokens(chains?, chainTypes?, minPriceUSD?)
- Get token informationlifi_get_token(chain, token)
- Get specific token details
Infrastructure
lifi_get_tools(chains?)
- List available bridges and exchangeslifi_get_connections(fromChain?, toChain?, fromToken?, toToken?, allowBridges?, denyBridges?, allowExchanges?, denyExchanges?)
- Get connection information
Gas & Pricing
lifi_get_gas_prices(chainId)
- Get current gas priceslifi_get_gas_suggestion(chain, fromChain?, fromToken?)
- Get gas recommendations
Transaction Management
lifi_get_transaction_status(txHash?, transactionId?)
- Track transaction statuslifi_get_integrator_fee_withdrawal(integratorId, chainId, tokens?)
- Manage fee withdrawals
Tech Stack
- Runtime: TypeScript
- MCP SDK: @modelcontextprotocol/sdk
- HTTP Client: node-fetch
- Validation: Zod
- Development: Smithery CLI
Error Handling
The server includes comprehensive error handling for:
- API authentication failures
- Network connectivity issues
- Invalid parameter validation
- LI.FI API errors and rate limits
All errors are returned as structured responses with descriptive messages.
Security
- API keys are required and validated at connection time
- All requests use HTTPS
- Input validation using Zod schemas
- No sensitive data is logged in production
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request
License
ISC
Support
For issues related to:
- This MCP Server: Create an issue in this repository
- LI.FI API: Visit LI.FI Documentation
- Model Context Protocol: Visit MCP Documentation
Changelog
v1.0.0
- Initial release with full LI.FI API integration
- Support for all major LI.FI endpoints
- Comprehensive error handling and validation
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.