Spaces:
Running
Running
Merge pull request #985 from mossbanay/mossbanay/fix-linkrot
Browse files
docs/integrations/chatgpt.mdx
CHANGED
|
@@ -13,7 +13,7 @@ MCP integration with ChatGPT is currently limited to **Deep Research** functiona
|
|
| 13 |
</Note>
|
| 14 |
|
| 15 |
<Tip>
|
| 16 |
-
OpenAI's official MCP documentation and examples are built with **FastMCP v2**! Check out their [sample MCP server](https://github.com/openai/
|
| 17 |
</Tip>
|
| 18 |
|
| 19 |
## Deep Research
|
|
@@ -42,7 +42,7 @@ A Deep Research-compatible server must implement these two required tools:
|
|
| 42 |
|
| 43 |
The `search` tool should take a query (of any kind!) and return IDs. The `fetch` tool should take an ID and return the record.
|
| 44 |
|
| 45 |
-
Here's a reference server implementation you can adapt (see also [OpenAI's sample server](https://github.com/openai/
|
| 46 |
|
| 47 |
```python server.py [expandable]
|
| 48 |
import json
|
|
|
|
| 13 |
</Note>
|
| 14 |
|
| 15 |
<Tip>
|
| 16 |
+
OpenAI's official MCP documentation and examples are built with **FastMCP v2**! Check out their [sample Deep Research style MCP server](https://github.com/openai/sample-deep-research-mcp) which demonstrates FastMCP in action.
|
| 17 |
</Tip>
|
| 18 |
|
| 19 |
## Deep Research
|
|
|
|
| 42 |
|
| 43 |
The `search` tool should take a query (of any kind!) and return IDs. The `fetch` tool should take an ID and return the record.
|
| 44 |
|
| 45 |
+
Here's a reference server implementation you can adapt (see also [OpenAI's sample server](https://github.com/openai/sample-deep-research-mcp) for comparison):
|
| 46 |
|
| 47 |
```python server.py [expandable]
|
| 48 |
import json
|