Delora MCP
Enables cross-chain quote retrieval, chain/token information, and tool discovery via the Delora API.
README
Delora MCP
MCP (Model Context Protocol) server for the Delora API: cross-chain quotes, supported chains, tokens, and tools.
Install
npm install
Configuration
Copy env.example to .env and adjust:
| Variable | Description | Default |
|---|---|---|
DELORA_API_URL |
Delora API base URL | https://api.delora.build |
DELORA_API_KEY |
Optional API key forwarded to Delora API as x-api-key |
unset |
MCP_TRANSPORT |
stdio or http |
stdio |
PORT |
HTTP server port (when MCP_TRANSPORT=http) |
3000 |
HOST |
HTTP bind address | 0.0.0.0 |
When DELORA_API_KEY is set, the MCP server forwards it to Delora API as the x-api-key header. In HTTP mode, the server also accepts incoming x-api-key or Authorization: Bearer ... headers and forwards the resolved key upstream. For HTTP requests, incoming headers take priority over DELORA_API_KEY. For stdio, DELORA_API_KEY remains the way to provide the key.
Run
Stdio (default) — for Cursor/IDE MCP over stdio:
npm run dev
# or
npm run build && npm start
HTTP — for streamable HTTP (e.g. behind a reverse proxy):
npm run dev:http
# or
npm run build && npm run start:http
Server listens on http://0.0.0.0:3000/mcp.
Cursor configuration
Stdio:
{
"mcpServers": {
"delora": {
"command": "node",
"args": ["/path/to/delora-mcp/dist/index.js"]
}
}
}
Streamable HTTP (e.g. after deploying to https://mcp.delora.build):
{
"mcpServers": {
"delora": {
"url": "https://mcp.delora.build/mcp",
"transport": "streamable-http",
"headers": {
"x-api-key": "YOUR_API_KEY"
}
}
}
}
You can also use Authorization: Bearer YOUR_API_KEY instead of x-api-key when your MCP client supports custom HTTP headers.
Docker
Build and run:
docker build -t delora-mcp .
docker run -p 3000:3000 -e MCP_TRANSPORT=http delora-mcp
For production behind a domain (e.g. mcp.delora.build): run the container with MCP_TRANSPORT=http and put nginx/traefik (or another reverse proxy) in front with HTTPS; then use the URL https://mcp.delora.build/mcp with streamable-http in Cursor.
API
- Delora API — base URL for all
/v1/*endpoints (quotes, chains, tokens, tools, token).
Tools
| Tool | Description |
|---|---|
get_instructions |
Returns this guide (call first for workflow). |
get_quote |
GET /v1/quotes — cross-chain quote. |
get_chains |
GET /v1/chains — supported chains. |
get_tools |
GET /v1/tools — available tools. |
get_tokens |
GET /v1/tokens — supported tokens. |
get_token |
GET /v1/token — single token by chain + token. |
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。