Remote MCP

Remote MCP quickstart

Deploy the Paradex MCP server to a cloud platform and connect your AI client via a public URL.

Remote deployments do not support trading at the moment. Only public market data is available. Use a local setup for full API access including trading.

How it works

The MCP server supports two transport modes controlled by MCP_TRANSPORT:

ModeValueUse case
stdio (default)stdioClaude Desktop, Claude Code, Cursor — runs as a local subprocess
HTTPstreamable-httpChatGPT Desktop, Claude.ai web, any remote client

In HTTP mode the server listens on MCP_PORT (default 3000) and exposes:

  • POST /mcp — MCP protocol endpoint (what clients connect to)
  • GET /health — health check, returns {"status": "ok"}

For more details, see the deploy-http guide in the repository.

Environment variables

VariableDescriptionDefault
MCP_TRANSPORTSet to streamable-http for remote deploymentstdio
MCP_PORTPort the HTTP server listens on3000
PARADEX_ENVIRONMENTTarget environment: prod, testnet, or nightlyprod

Most platforms let you set these as environment variables in their dashboard. If you’ve cloned the MCP server repository to build and deploy, you can also store them in a .env file at the repo root:

$cp .env.template .env

Then edit .env with your values. The server loads this file automatically on startup.

Choose a platform

OptionEffortCostBest for
RailwayLow~$5/moQuickest permanent setup
RenderLowFree tier availableLow-traffic / evaluation
Fly.ioMedium~$2–5/moGlobal, low-latency
AWS LambdaMediumPay-per-requestScalable, zero idle cost
Docker / VPSHighVariesFull control

All options produce an endpoint of the form https://your-domain.example.com/mcp that you paste into your AI client’s MCP settings.

Verify your deployment

Test your endpoint from the terminal (replace the URL with your actual deployment URL):

$curl https://your-endpoint.example.com/health
$# Expected: {"status":"ok"}
$
$curl -X POST https://your-endpoint.example.com/mcp \
>  -H "Content-Type: application/json" \
>  -d '{"jsonrpc":"2.0","method":"tools/list","id":1}'
$# Expected: JSON list of available tools

Connect your AI client

  1. Open claude.ai → Settings → Integrations.
  2. Click Add MCP Server.
  3. Enter your endpoint URL (e.g. https://your-domain.example.com/mcp).