graph-lending-mcp
MCP server that exposes unified AI-friendly tools over Messari's standardized lending subgraphs on The Graph. One natural-language query → fan out across 40+ lending protocols on multiple chains → get back structured, comparable data.
README
graph-lending-mcp
<a href="https://glama.ai/mcp/servers/@PaulieB14/graph-lending-mcp"> <img width="380" height="200" src="https://glama.ai/mcp/servers/@PaulieB14/graph-lending-mcp/badge" /> </a>
MCP server that exposes unified AI-friendly tools over Messari's standardized lending subgraphs on The Graph.
One natural-language query → fan out across 40+ lending protocols on multiple chains → get back structured, comparable data.
<a href="https://glama.ai/mcp/servers/@PaulieB14/graph-lending-mcp"> <img width="380" height="200" src="https://glama.ai/mcp/servers/@PaulieB14/graph-lending-mcp/badge" alt="graph-lending-mcp MCP server" /> </a>
Features
- 19 MCP tools covering protocols, markets, rates, positions, events, snapshots, and cross-protocol analytics
- 40+ lending protocols across Ethereum, Polygon, Arbitrum, Avalanche, BSC, Optimism, Base, and more
- Cross-protocol comparison — compare TVL, revenue, users across any set of protocols in one call
- Graceful failure handling — dead subgraphs don't crash queries; failures are reported alongside successes
- Schema-version aware — automatically selects compatible queries for v1.x, v2.x, and v3.x subgraphs
Tools
| Tool | Description |
|---|---|
list_protocols |
List all registered protocols with live TVL data |
get_protocol |
Detailed protocol stats (TVL, revenue, users, pool counts) |
get_markets |
List markets for a protocol, sorted by any field |
get_market |
Detailed single market data including rates, caps, and positions |
get_interest_rates |
Interest rates across all markets, with optional side/type filters |
get_account |
Account overview with position counts and activity |
get_positions |
Open positions for an address, with optional side filter |
get_deposits |
Recent deposit events, filterable by market and account |
get_borrows |
Recent borrow events |
get_repays |
Recent repay events |
get_withdrawals |
Recent withdrawal events |
get_liquidations |
Recent liquidation events with profit data |
get_flashloans |
Recent flashloan events |
get_daily_financials |
Daily financial snapshots (TVL, volume, revenue) |
get_market_snapshots |
Daily market-level snapshots with rates and activity |
get_usage_metrics |
Daily user activity and transaction counts |
compare_protocols |
Side-by-side comparison of multiple protocols |
top_markets_by_tvl |
Top markets across all protocols, optionally filtered by network |
query_subgraph |
Raw GraphQL escape hatch for any registered subgraph |
Setup
Prerequisites
- Node.js 18+
- A Graph API key from The Graph Studio
Install & Build
git clone https://github.com/PaulieB14/graph-lending-mcp.git
cd graph-lending-mcp
npm install
npx tsc
Configure in Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"graph-lending": {
"command": "node",
"args": ["/path/to/graph-lending-mcp/dist/index.js"],
"env": {
"GRAPH_API_KEY": "your-api-key-here"
}
}
}
}
Architecture
src/
├── index.ts # MCP server entry — registers all 19 tools
├── registry.ts # Protocol → subgraph ID mapping (see SUBGRAPHS.md)
├── client.ts # GraphQL fetch with retry, timeout, fan-out
├── queries.ts # All GraphQL query constants
└── tools/
├── protocol.ts # list_protocols, get_protocol
├── markets.ts # get_markets, get_market
├── rates.ts # get_interest_rates
├── positions.ts # get_account, get_positions
├── events.ts # deposits, borrows, repays, withdrawals, liquidations, flashloans
├── snapshots.ts # daily_financials, market_snapshots, usage_metrics
└── cross.ts # compare_protocols, top_markets_by_tvl
All queries use Messari's standardized lending schema — same entities and fields across every protocol.
Subgraph Registry
See SUBGRAPHS.md for the full list of registered subgraphs with their status, network, schema version, and notes.
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。