ChatGPT × Hyperliquid
ChatGPT and the OpenAI stack — three routes to the same engine.
ChatGPT Desktop Connectors and the OpenAI Codex CLI both speak MCP. Custom GPTs call the Keel REST API through Actions. All three routes drive the same deterministic Hyperliquid backtest engine — composition, backtest, and non-custodial live execution. Pick the route that matches your workflow.
Three routes, one engine
ChatGPT Desktop, Codex CLI, and custom GPTs each connect differently.
The OpenAI ecosystem reaches Keel three ways. Two of them use MCP directly; one uses REST through Actions. None of them put the LLM in the trade-execution loop — the compiled strategy runs on its own schedule.
ChatGPT Desktop Connectors
In-chat MCP access. On Pro, Business, and Enterprise tiers, register Keel as a Connector and ChatGPT can call its tools — compose a strategy, run a backtest, pull a tearsheet — without leaving the chat window. Same 22-tool surface other MCP hosts see.
With Keel
Best for users who live in the ChatGPT app and want strategy authoring as a conversation. The agent calls Keel tools by name; results stream back inline.
OpenAI Codex CLI
A terminal-native developer agent with native MCP support. Add Keel to your Codex config, run codex in any project, and the agent can search components, compose strategies, run backtests, and fork variants — same protocol Claude Code and Cursor use over stdio.
With Keel
Best for users whose workflow lives in the terminal. Pair with your editor of choice. The CLI's agent loop handles long-running backtests and multi-step composition cleanly.
Custom GPT with Actions
Lightweight REST-based integration. Build a custom GPT, import the Keel OpenAPI spec, add an API key. The GPT can pull funding rates, summarize backtests, and check account state. Doesn't require installing a CLI or running anything locally.
With Keel
Best for read-heavy flows and shareable assistants. Anyone with the GPT link can use it. Less suited to long-running strategy authoring than the MCP routes, but powerful for analyst and review work.
Install per route
Pick a route. Run the snippet. The agent has access.
Route A registers Keel as an MCP Connector in ChatGPT Desktop. Route B does the same for the Codex CLI. Route C imports the Keel OpenAPI spec into a custom GPT for REST-based flows.
Route A
ChatGPT Desktop Connectors
In-chat MCP. Register Keel as a Connector in ChatGPT Desktop (Pro / Business / Enterprise) and the agent has direct tool access.
$ pipx install keel-trade
# In ChatGPT Desktop:
# Settings → Connectors → Add
# Type: Local MCP (stdio)
# Command: keel
# Args: ["mcp", "serve"]
# Then in chat:
# "Connect to Keel and compose a funding-carry
# strategy for Hyperliquid."
Route B
OpenAI Codex CLI
Terminal-native MCP. Pass the server config to Codex at startup, or register it in your Codex config file.
$ pipx install keel-trade
# Inline at launch:
$ codex --mcp-config '{"keel":{"command":"keel","args":["mcp","serve"]}}'
# Or persist in ~/.codex/config.toml:
# [mcp_servers.keel]
# command = "keel"
# args = ["mcp", "serve"]
# Run codex in your project; ask for Keel.
Route C
Custom GPT with Actions
REST-based. Build a custom GPT, import the Keel OpenAPI spec, add an API key. Good for read-only and shareable flows.
# In ChatGPT (Plus / Team / Enterprise):
# 1. Create a new GPT
# 2. Configure → Actions → Import from URL
# https://api.usekeel.io/openapi.json
# 3. Add auth: API key from Keel settings
# Then in chat:
# "What's the funding rate on HYPE right now?"
# "Summarize backtest run btr_abc..."
FAQ
Common questions
How do I connect ChatGPT to Hyperliquid?
Three routes today. (1) ChatGPT Desktop with Connectors — Pro, Business, and Enterprise tiers can register MCP servers as Connectors and call their tools from chat. (2) The OpenAI Codex CLI — a developer agent that speaks MCP natively over stdio. (3) A custom GPT with Actions — uploads the Keel OpenAPI spec and calls REST endpoints. Pick the route that fits your workflow; each one drives the same engine.
Does ChatGPT support MCP?
Yes, on two surfaces. ChatGPT Desktop on paid tiers exposes Connectors, which run MCP servers underneath. The OpenAI Codex CLI supports MCP stdio servers the same way Claude Code, Cursor, and Windsurf do. Custom GPTs on the consumer web app use Actions instead — REST calls against an OpenAPI spec — which is a different protocol but still gets you to the same Keel surface.
Which route should I pick?
ChatGPT Desktop Connectors if you live in the ChatGPT app and want in-chat strategy authoring. The Codex CLI if your work is terminal-driven and you want a developer agent next to your editor. A custom GPT with Actions if you want a lightweight read-only assistant — funding lookups, tearsheet summaries, account checks — without installing anything locally.
Can ChatGPT or Codex trade my Hyperliquid account autonomously?
No. With any of the three routes, the LLM helps you compose a strategy and run a backtest. The compiled strategy artifact is what trades — it runs on its own schedule, on the same execution path the backtest used. The LLM is not in the runtime loop. Live execution requires explicit OAuth scope and a separate local arming step; non-custodial throughout via Hyperliquid native delegated signing.
Can I trigger a Keel backtest from ChatGPT?
Yes from all three routes. Desktop Connectors and the Codex CLI both call the backtest tool directly over MCP and stream results back into the conversation. A custom GPT with Actions calls the same backtest endpoint over REST — slightly more polling involved for long-running jobs, but you get the same artifact and the same share URL.
Where do I get the OpenAPI spec or the MCP install snippet?
For Connectors and Codex CLI, install the Keel package (pipx install keel-trade) and point your config at keel mcp serve — the per-host snippet matrix is documented at /docs/sdk/agent-setup. For a custom GPT, import the Keel OpenAPI spec from your account settings and add an API key. Both flows are documented in the getting-started guide.
Related
Keep exploring
The Keel MCP server
Product page for the MCP. Install path, tool surface, browser OAuth, and the full per-host config matrix.
Claude × Hyperliquid
Sibling page for Claude Code, Claude Desktop, and Cursor. Same engine, different host.
Build a trading strategy with an agent
Step-by-step tutorial covering composition, backtest, and non-custodial live deploy through any MCP-capable agent.
Non-custodial
Your keys never leave your wallet. Your strategies run on your account — Keel never holds funds.
Same code, backtest to live
The strategy that passed your backtest is the strategy that trades. Same pipeline, no surprises.
Full visibility
See every position, trade, and decision in real time. Pause anytime. Your account, your control.