---
title: Use Hive with OpenAI and ChatGPT
lastUpdated: '2026-06-03'
nextjs:
  metadata:
    title: "Use Hive with OpenAI and ChatGPT | Crypto Data for AI Agents"
    description: "Use Hive's live crypto tools from OpenAI's Responses API remote MCP path, or plan a ChatGPT app integration with the current beta auth limits in mind."
    alternates:
      canonical: https://www.hiveintelligence.xyz/install/chatgpt
    keywords: "chatgpt crypto, openai mcp crypto, hive chatgpt, chatgpt crypto data, openai crypto mcp"
---

**Use Hive from OpenAI when your agent needs live crypto prices, wallets, DeFi, and token-risk checks instead of training-cutoff answers.** The reliable path today is the OpenAI Responses API remote MCP tool or Hive's REST API. Direct ChatGPT app setup is beta and depends on the auth flow your workspace can use. {% .lead %}

{% ai-doc-actions path="/install/chatgpt" title="OpenAI and ChatGPT Install Guide" /%}

---

## Current compatibility

Hive's public MCP endpoint is `https://mcp.hiveintelligence.xyz/mcp` and requires API-key authentication (`Authorization: Bearer <YOUR_HIVE_API_KEY>`).

OpenAI currently exposes two relevant MCP paths:

- **Responses API remote MCP** — server-side code can provide a remote MCP `server_url` and an `authorization` token in the `tools` array.
- **ChatGPT developer-mode apps** — OpenAI documents web-based ChatGPT apps in beta. Current ChatGPT app setup advertises OAuth, no-auth, and mixed auth flows. Hive has not shipped OAuth/CIMD yet, so the public Hive endpoint is not currently a direct ChatGPT UI connector.

If your ChatGPT workspace asks for OAuth when creating an app, use the Responses API or Hive REST examples below, or put an OAuth-compatible proxy in front of Hive.

---

## Before you start

1. A Hive API key from [/dashboard/keys](/dashboard/keys).
2. An OpenAI API key if you are using the Responses API.
3. Optional: a ChatGPT workspace with developer mode enabled if you are testing a custom ChatGPT app.

Keep both keys on your server. Do not paste production keys into prompts or client-side code.

---

## Recommended: Responses API remote MCP

Use Hive as a remote MCP tool from server-side OpenAI API code:

```ts
import OpenAI from "openai";

const openai = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });

const response = await openai.responses.create({
  model: "gpt-5",
  input: "Use Hive to get the current BTC and ETH prices in USD.",
  tools: [
    {
      type: "mcp",
      server_label: "hive",
      server_description: "Live crypto market, wallet, DeFi, and token-risk tools from Hive Intelligence.",
      server_url: "https://mcp.hiveintelligence.xyz/mcp",
      authorization: process.env.HIVE_API_KEY,
      allowed_tools: [
        "search_tools",
        "get_api_endpoint_schema",
        "invoke_api_endpoint",
      ],
    },
  ],
});

console.log(response.output_text);
```

That keeps OpenAI orchestration in your app while Hive handles live crypto data, tool discovery, upstream provider auth, and normalized execution metadata. The `allowed_tools` list imports Hive's root discovery loop instead of exposing every category-listing helper to the model.

OpenAI's remote MCP flow first imports tools from the server as an `mcp_list_tools` output item, then emits an `mcp_call` item when the model calls a tool. For Hive, the expected root flow is:

1. `search_tools` to find the right Hive task/tool.
2. `get_api_endpoint_schema` when the argument shape is unknown.
3. `invoke_api_endpoint` to execute the selected Hive provider tool.

For production workflows, keep OpenAI's default approval flow enabled until you have reviewed the tool names, arguments, and returned data. Only use `require_approval: "never"` or a narrower `require_approval` object after you have a logged allowlist for low-risk tool calls. See OpenAI's [MCP and connectors guide](https://developers.openai.com/api/docs/guides/tools-connectors-mcp) for `allowed_tools`, `mcp_list_tools`, `mcp_call`, and approval behavior.

### Verify it worked

Run the example with a valid OpenAI key and Hive key, then inspect the response output. A successful OpenAI-side run should include:

- an `mcp_list_tools` item for `server_label: "hive"` with the allowed Hive root tools
- an `mcp_call` item whose `name` is usually `search_tools`, `get_api_endpoint_schema`, or `invoke_api_endpoint`
- current BTC/ETH data in the tool output, with Hive metadata such as provider, runtime status, and freshness when the invoked provider tool returns it

If the model answers without using Hive, inspect the Responses API event stream or output array and confirm the `server_url`, `authorization`, and `allowed_tools` fields are present.

---

## Alternative: call Hive REST from your OpenAI agent

If you want explicit control over tool routing, expose Hive REST calls as your own function tools:

```bash
curl -X POST https://mcp.hiveintelligence.xyz/api/v1/execute \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_HIVE_API_KEY" \
  -d '{"tool":"get_price","args":{"ids":"bitcoin,ethereum","vs_currencies":"usd"}}'
```

Use this path when your agent framework already wraps HTTP tools, when a ChatGPT UI connector requires OAuth, or when you need custom rate limiting and logging before Hive calls.

---

## ChatGPT app beta notes

OpenAI's ChatGPT app/developer-mode surface is changing quickly. As of this page's last update:

- Full ChatGPT MCP app support is beta and workspace/plan-dependent.
- OpenAI's developer-mode docs list SSE and Streamable HTTP as supported protocols.
- The documented ChatGPT app auth choices are OAuth, no authentication, and mixed authentication.
- Hive's public endpoint requires a Hive API key and does not yet implement OAuth/CIMD.

For a production ChatGPT app, build an OAuth-compatible adapter or proxy that validates the ChatGPT-side user, injects the Hive API key server-side, and forwards calls to Hive. For local development or backend agents, prefer the Responses API MCP path above.

---

## What to ask once connected

- *"Use Hive to get BTC, ETH, and SOL prices in USD."*
- *"Check whether 0x6B175474E89094C44Da98b954EedeAC495271d0F has token-security risks."*
- *"Show the top DeFi protocols by TVL on Ethereum and note 24-hour changes."*
- *"Summarize this wallet's balances, NFT holdings, and risky token approvals."*

---

## Troubleshooting

**The MCP connection fails.** Check that the URL is exactly `https://mcp.hiveintelligence.xyz/mcp` and that your server passes the Hive API key as the MCP authorization token or as `Authorization: Bearer YOUR_HIVE_API_KEY` for REST calls.

**ChatGPT asks for OAuth.** Hive has not implemented OAuth/CIMD yet. Use the Responses API MCP example, Hive REST, or an OAuth-compatible proxy that forwards to Hive with a server-side Hive key.

**Tools do not appear.** Confirm the caller can reach `mcp.hiveintelligence.xyz` over HTTPS and that the key is valid at [/dashboard/keys](/dashboard/keys).

**The model cannot call the price tool directly.** On Hive's root `/mcp`, provider tools are reached through `invoke_api_endpoint` after discovery/schema lookup. Either keep `invoke_api_endpoint` in `allowed_tools`, or connect to a category-scoped Hive endpoint when you intentionally want direct category tools.

**You need a local MCP client instead.** Use [Claude Desktop](/install/claude-desktop), [Claude Code](/install/claude-code), [Cursor](/install/cursor), [Windsurf](/install/windsurf), [VS Code](/install/vs-code), [Codex CLI](/install/codex), or [Gemini CLI](/install/gemini-cli).

---

## Next steps

- [Agent Resources](/ai-agent-hub) — prompts, skills, and runtime resources
- [REST API](/api-integration) — direct backend integration
- [Tools Reference](/tools) — every callable Hive tool