NEAR DeFi Dashboard
Enables Claude to access real-time NEAR DeFi data for yield comparisons, staking analysis, swap routing, and lending rates, helping users make informed DeFi decisions.
README
MCP Server: NEAR DeFi Dashboard
An MCP (Model Context Protocol) server that provides Claude with real-time NEAR DeFi data, enabling intelligent yield recommendations, portfolio analysis, and swap routing.
Features
- DeFi Yields: Real-time APY data from Ref Finance, Burrow, Meta Pool, and Linear Protocol
- Staking Comparison: Compare native staking vs liquid staking vs DeFi yields
- Swap Routing: Find optimal token swap routes on Ref Finance
- Lending Rates: Current supply/borrow rates on Burrow
- IL Calculator: Impermanent loss calculator for LP positions
Installation
npm install @near-mcp/defi-dashboard
Or run directly:
npx @near-mcp/defi-dashboard
Claude Desktop Configuration
Add to your Claude Desktop config:
{
"mcpServers": {
"near-defi": {
"command": "npx",
"args": ["@near-mcp/defi-dashboard"]
}
}
}
Available Tools
1. get_defi_yields
Get current APY across all major NEAR DeFi protocols.
Example Conversation:
User: What are the best yields on NEAR right now?
Claude: [uses get_defi_yields]
Here are the top yields on NEAR DeFi:
1. Ref Finance NEAR-USDC LP: 25% APY ($2.5M TVL) - Medium risk
2. Meta Pool stNEAR: 9.5% APY ($15M TVL) - Low risk
3. Linear LiNEAR: 9.2% APY ($12M TVL) - Low risk
4. Burrow Supply USDT: 5.2% APY - Low risk
Input:
{
"min_apy": 5,
"max_risk": "medium",
"type": "all"
}
2. compare_staking_options
Compare different ways to earn yield on NEAR.
Example Conversation:
User: I have 1000 NEAR, what should I do with it?
Claude: [uses compare_staking_options with amount="1000"]
Here's a comparison for your 1000 NEAR over 1 year:
| Option | APY | Return | Risk |
|--------|-----|--------|------|
| Native Staking | 9.8% | 98 NEAR | Low |
| stNEAR | 9.5% | 95 NEAR | Low |
| LP (NEAR-USDC) | 25% | 250 NEAR | Medium |
Recommendation: For 1000+ NEAR, consider splitting: 50% native, 30% liquid, 20% DeFi.
3. find_best_swap_route
Find optimal swap routes on Ref Finance.
Example:
{
"from_token": "wrap.near",
"to_token": "usdt.tether-token.near",
"amount": "100"
}
Output:
{
"route": "wrap.near → usdt.tether-token.near",
"expected_output": "450.123456",
"price_impact": "0.10%",
"fees": "0.3%"
}
4. get_lending_rates
Get Burrow lending protocol rates.
Example Conversation:
User: What are the lending rates on Burrow?
Claude: [uses get_lending_rates]
Current Burrow rates:
- NEAR: 3.5% supply / 8.2% borrow (45% utilized)
- USDT: 5.2% supply / 12.1% borrow (62% utilized)
- USDC: 4.8% supply / 11.5% borrow (58% utilized)
5. calculate_impermanent_loss
Calculate IL for LP positions.
Example:
{
"token_a": "NEAR",
"token_b": "USDC",
"price_change_pct": 50,
"initial_value_usd": 1000
}
Output:
{
"impermanent_loss": "2.02%",
"value_if_held": "$750.00",
"value_as_lp": "$734.85",
"loss_vs_holding": "$15.15"
}
Data Sources
- Ref Finance: DEX pools, liquidity, swap rates
- Burrow: Lending/borrowing rates
- Meta Pool: stNEAR staking stats
- Linear Protocol: LiNEAR staking stats
Caching
Data is cached for 5 minutes to avoid rate limiting. The cache automatically refreshes on expiry.
Development
npm install
npm run build
npm start
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.
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.