ChatGPT Desktop

Connect the Paradex MCP server to ChatGPT Desktop in a few steps.

ChatGPT Desktop

Connect the Paradex MCP server to ChatGPT Desktop in a few steps.

ChatGPT Desktop cannot run local programs directly, so you use ngrok to create a tunnel from your local MCP server to a public URL that ChatGPT can connect to.

Complete prerequisites

Follow the Prerequisites guide to install Python, uvx, and get your Paradex private key.

Install ngrok

$ brew install ngrok   # macOS
$ # Or download from https://ngrok.com

Start the MCP server

$ MCP_TRANSPORT=streamable-http MCP_PORT=8080 \
> PARADEX_ENVIRONMENT=prod \
> PARADEX_ACCOUNT_PRIVATE_KEY=your_private_key_here \
> uvx mcp-paradex

Replace your_private_key_here with your actual key.

Open a tunnel

In a second terminal:

$ ngrok http 8080

Copy the https://xxxx.ngrok-free.app URL from the output.

Connect in ChatGPT

Open ChatGPT Desktop → Settings → Advanced → Developer Mode (enable if not already).
Go to Settings → Connectors → Create.
Paste https://xxxx.ngrok-free.app/mcp.
Click I trust this provider.

Limitation: The tunnel URL changes every time you restart ngrok (free tier). Update the connector URL each session.

Verify it’s working

Ask your AI assistant:

“What markets are available on Paradex?”

If you get a list of trading pairs, you’re connected.

To test trading access, ask:

“Show me my Paradex account summary.”

OpenAI Agents SDK (for developers)

For custom Python apps (not the ChatGPT interface). No remote hosting needed.

$ pip install openai-agents

1 import asyncio, os
2 from agents import Agent, Runner
3 from agents.mcp import MCPServerStdio
4 
5 async def main():
6     async with MCPServerStdio(
7         name="paradex",
8         params={
9             "command": "uvx",
10             "args": ["mcp-paradex"],
11             "env": {
12                 **os.environ,
13                 "PARADEX_ENVIRONMENT": "prod",
14                 "PARADEX_ACCOUNT_PRIVATE_KEY": "your_private_key_here",
15             },
16         },
17     ) as server:
18         agent = Agent(
19             name="Paradex Trader",
20             instructions="You are a trading assistant with access to Paradex.",
21             mcp_servers=[server],
22         )
23         result = await Runner.run(agent, "What are the top markets by volume?")
24         print(result.final_output)
25 
26 asyncio.run(main())

ChatGPT Desktop cannot run local programs directly, so you use ngrok to create a tunnel from your local MCP server to a public URL that ChatGPT can connect to.

Complete prerequisites

Follow the Prerequisites guide to install Python, uvx, and get your Paradex private key.

Install ngrok

$ brew install ngrok   # macOS
$ # Or download from https://ngrok.com

Start the MCP server

$ MCP_TRANSPORT=streamable-http MCP_PORT=8080 \
> PARADEX_ENVIRONMENT=prod \
> PARADEX_ACCOUNT_PRIVATE_KEY=your_private_key_here \
> uvx mcp-paradex

Replace your_private_key_here with your actual key.

Open a tunnel

In a second terminal:

$ ngrok http 8080

Copy the https://xxxx.ngrok-free.app URL from the output.

Connect in ChatGPT

Open ChatGPT Desktop → Settings → Advanced → Developer Mode (enable if not already).
Go to Settings → Connectors → Create.
Paste https://xxxx.ngrok-free.app/mcp.
Click I trust this provider.

Limitation: The tunnel URL changes every time you restart ngrok (free tier). Update the connector URL each session.

Verify it’s working

Ask your AI assistant:

“What markets are available on Paradex?”

If you get a list of trading pairs, you’re connected.

To test trading access, ask:

“Show me my Paradex account summary.”

OpenAI Agents SDK (for developers)

For custom Python apps (not the ChatGPT interface). No remote hosting needed.

$ pip install openai-agents

1 import asyncio, os
2 from agents import Agent, Runner
3 from agents.mcp import MCPServerStdio
4 
5 async def main():
6     async with MCPServerStdio(
7         name="paradex",
8         params={
9             "command": "uvx",
10             "args": ["mcp-paradex"],
11             "env": {
12                 **os.environ,
13                 "PARADEX_ENVIRONMENT": "prod",
14                 "PARADEX_ACCOUNT_PRIVATE_KEY": "your_private_key_here",
15             },
16         },
17     ) as server:
18         agent = Agent(
19             name="Paradex Trader",
20             instructions="You are a trading assistant with access to Paradex.",
21             mcp_servers=[server],
22         )
23         result = await Runner.run(agent, "What are the top markets by volume?")
24         print(result.final_output)
25 
26 asyncio.run(main())

$	brew install ngrok # macOS
$	# Or download from https://ngrok.com

$	MCP_TRANSPORT=streamable-http MCP_PORT=8080 \
>	PARADEX_ENVIRONMENT=prod \
>	PARADEX_ACCOUNT_PRIVATE_KEY=your_private_key_here \
>	uvx mcp-paradex

1	import asyncio, os
2	from agents import Agent, Runner
3	from agents.mcp import MCPServerStdio
4
5	async def main():
6	async with MCPServerStdio(
7	name="paradex",
8	params={
9	"command": "uvx",
10	"args": ["mcp-paradex"],
11	"env": {
12	**os.environ,
13	"PARADEX_ENVIRONMENT": "prod",
14	"PARADEX_ACCOUNT_PRIVATE_KEY": "your_private_key_here",
15	},
16	},
17	) as server:
18	agent = Agent(
19	name="Paradex Trader",
20	instructions="You are a trading assistant with access to Paradex.",
21	mcp_servers=[server],
22	)
23	result = await Runner.run(agent, "What are the top markets by volume?")
24	print(result.final_output)
25
26	asyncio.run(main())