Building MCP servers for ChatGPT and API integrations
platform.openai.com
Building MCP servers for ChatGPT and API integrations
1–10 of 31 posts
Re: Building MCP servers for ChatGPT and API integrations
#2Is it safe to say that MCP has "won" vs. A2A? Or is this a misreading of the situation?
Re: Building MCP servers for ChatGPT and API integrations
#3The support here is really weird.
If I understand correctly, it requires your MCP server to have exactly two tools - search and fetch.
So this is not really support for MCP in general, as in all the available MCP servers. It’s support for their own custom higher-level protocol built on top of MCP.
Re: Building MCP servers for ChatGPT and API integrations
#4The support here is really weird. If I understand correctly, it requires your MCP server to have exactly two tools - search and fetch. So this is not really support for MCP in general, as in all the available MCP servers. It’s support for their own custom higher-level protocol built on top of MCP.
Yeah I hope they open up support to all MCP tools - this is lame as-is.
Re: Building MCP servers for ChatGPT and API integrations
#5The support here is really weird. If I understand correctly, it requires your MCP server to have exactly two tools - search and fetch. So this is not really support for MCP in general, as in all the available MCP servers. It’s support for their own custom higher-level protocol built on top of MCP.
this guide is just for an example of how to build a single mcp (e.g. a vector store). chatgpt connectors implement mcps in general now
Re: Building MCP servers for ChatGPT and API integrations
#6Is it safe to say that MCP has "won" vs. A2A? Or is this a misreading of the situation?
I think they have different use cases. MCP is for tool calling, A2A for agents communicating between themselves.
Re: Building MCP servers for ChatGPT and API integrations
#7Is it safe to say that MCP has "won" vs. A2A? Or is this a misreading of the situation?
They're not directly solving the same problem. MCP is for exposing tools, such as reading files. a2a is for agents to talk to other agents to collaborate.
MCP servers can expose tools that are agents, but don't have to, and usually don't.
That being said, I can't say I've come across an actual implementation of a2a outside of press releases...
Re: Building MCP servers for ChatGPT and API integrations
#8Has something changed? That seems to be the same page they've had for a couple of months. It's only for deep research mode, and is restricted to Pro and Enterprise.
Re: Building MCP servers for ChatGPT and API integrations
#9Title is mildly misleading, is only available for the API, not the web/mobile interface.
Re: Building MCP servers for ChatGPT and API integrations
#10The support here is really weird. If I understand correctly, it requires your MCP server to have exactly two tools - search and fetch. So this is not really support for MCP in general, as in all the available MCP servers. It’s support for their own custom higher-level protocol built on top of MCP.
this guide is just for an example of how to build a single mcp (e.g. a vector store). chatgpt connectors implement mcps in general now
I don’t believe this is the case. Do you have a link for that?
Cause from TFA “To work with ChatGPT Connectors or deep research (in ChatGPT or via API), your MCP server must implement two tools - search and fetch.”
Also, this page is actually the only docs site about MCP they have, and their help articles link to it too.