Fibrous MCP Server
Provides tools for multi-chain DeFi operations using the Fibrous SDK, enabling AI agents to find swap routes, build transactions, and execute swaps across Base, Starknet, and Scroll networks.
README
Fibrous MCP Server
MCP server providing AI agents with tools for multi-chain DeFi operations using the Fibrous SDK.
Features
10 Available Tools:
get-supported-tokens- List available tokensget-supported-protocols- List DEX protocolsget-best-route- Find optimal swap routesget-best-route-batch- Find optimal routes for batch swaps (Starknet only)build-transaction- Generate transaction databuild-batch-transaction- Generate batch transaction data (Starknet only)format-token-amount- Convert between human and wei formatsget-token- Fetch token details by addressexecute-swap- Execute token swaps (requires wallet config)estimate-swap- Estimate gas costs (requires wallet config)
Supported Networks:
- Base - Uniswap V3, Aerodrome, SwapBased
- Starknet - JediSwap, MySwap, 10kSwap, Ekubo
- Scroll - Uniswap V3, SyncSwap, iZiSwap
Quick Start
# Install dependencies
pnpm install
# Configure environment
cp .env.example .env
# Edit .env with your RPC URLs and private keys
# Build the project
pnpm build
# Start server
pnpm start
Configuration
Environment Variables
Core Configuration:
NODE_ENV=development
DEFAULT_SLIPPAGE=1.0
Network Configuration:
# Base Network
BASE_RPC_URL=https://mainnet.base.org
BASE_PRIVATE_KEY=0x...
# Starknet Network
STARKNET_RPC_URL=https://starknet-mainnet.public.blastapi.io
STARKNET_PRIVATE_KEY=0x...
STARKNET_PUBLIC_KEY=0x...
# Scroll Network
SCROLL_RPC_URL=https://rpc.scroll.io
SCROLL_PRIVATE_KEY=0x...
Optional Settings:
# Debug configuration
DEBUG=false
LOG_LEVEL=info
ENABLE_METRICS=false
# API optimization
FIBROUS_API_KEY=your_api_key_here
MCP Client Setup
Add to your MCP client configuration:
{
"mcpServers": {
"fibrous-mcp": {
"command": "node",
"args": ["/path/to/fibrous-mcp/build/src/index.js"]
}
}
}
Development
Prerequisites
- Node.js 18+
- pnpm (recommended)
- TypeScript 5.0+
Setup
# Clone repository
git clone <repository-url>
cd fibrous-mcp
# Install dependencies
pnpm install
# Start development server
pnpm dev
# Watch mode with auto-reload
pnpm dev:watch
Code Quality
# Type checking
pnpm typecheck
# Linting
pnpm lint
pnpm lint:fix
# Code formatting
pnpm format
pnpm format:check
Testing
Comprehensive test suite with 82.6% coverage across all modules:
# Run all tests
pnpm test
# Watch mode for development
pnpm test:watch
# Coverage report
pnpm test:coverage
# CI mode
pnpm test:ci
Test Results:
- 167/167 tests passing
- 10 test suites, ~3.1s execution
- Native BigInt with router-sdk v0.6.0
Test Coverage by Module
- API endpoints: 17 tests
- Server configuration: 14 tests
- Tool handlers: 14 tests
- Utilities: 122 tests (BigInt operations, configuration, responses, swap logic, validation)
Coverage Details
- Statements: 82.56%
- Branches: 73.46%
- Functions: 75.71%
- Lines: 83.18%
Technical Details
Native BigInt Integration
- Router SDK v0.6.0: Latest Fibrous SDK compatibility
- 50KB smaller bundle: Removed BigNumber.js dependency
- Faster calculations: Native JavaScript
bigintoperations - Modern standards: ES2022+ features
// Example: Native BigInt usage
const amount = BigInt("1000000000000000000"); // 1 ETH
const route = await router.getBestRoute(amount, tokenIn, tokenOut, "base");
Architecture
- MCP Protocol: Model Context Protocol compliance
- Type Safety: Full TypeScript implementation
- Error Handling: Comprehensive error management
- Security: Environment variable validation and masking
Production Deployment
Environment Setup
# Production build
pnpm build:clean
# Production start
NODE_ENV=production pnpm start:prod
Security Considerations
- Store private keys securely (use secrets management)
- Configure appropriate RPC endpoints
- Set up monitoring and logging
- Use HTTPS for all external connections
Performance
- Native BigInt: 2-3x faster than BigNumber.js
- Bundle Size: 50KB reduction vs v0.5.x
- Memory Usage: Optimized for long-running processes
- Rate Limiting: 200 req/min (configurable)
Resources
- Fibrous Finance - Main website
- Documentation - API docs
- MCP Protocol - MCP specifications
- Router SDK v0.6.0 - Local SDK documentation
API Endpoints:
- https://api.fibrous.finance (200 req/min)
- https://graph.fibrous.finance
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests for new functionality
- Ensure all tests pass:
pnpm test - Submit a pull request
Development Guidelines
- Follow TypeScript best practices
- Maintain test coverage above 75%
- Use conventional commit messages
- Update documentation for new features
License
MIT - see LICENSE
Risk Warning: DeFi operations involve financial risk. Always verify transactions and use testnet for development.
Status: Production ready with comprehensive test coverage and native BigInt support.
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.