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. |
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.
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.
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.
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.