"OpenAI has added a beta of Developer mode to ChatGPT, enabling full read and write support for MCP (Model Context Protocol) tools, though the documentation describes the feature as dangerous. Developer community lead Edwin Arbus said that "in developer mode, developers can create connectors and use them in chat for write actions (not just search/fetch). Update Jira tickets, trigger Zapier workflows or combine connectors for complex automations." Limitations in the initial beta are that developer mode does not work in Team workspaces or in project chats."
"Arbus demonstrated how the feature could link ChatGPT to Stripe so that the AI can raise invoices and send them in response to a prompt. There is a Confirm button before an action is taken but this can be disabled for a trusted MCP server by checking an option to "remember for this conversation." The response from users is enthusiastic in principle."
"Some users have encountered bugs, either with connectors not working, or returning fictional information. One user connected ChatGPT to Atlassian's Jira issue tracking tool, asked it to summarize an issue, and reported that the tool was called, returned data, but that "GPT completely make up the summary, it's something completely different than in the Jira issue.""
OpenAI released a beta Developer mode for ChatGPT that adds full read and write support for MCP (Model Context Protocol) tools, enabling connectors to perform write actions in chat. The beta excludes Team workspaces and project chats. Developers can create connectors to update Jira tickets, trigger Zapier workflows, or link services like Stripe to raise and send invoices on prompt. A Confirm button appears before write actions but can be disabled for trusted MCP servers. Users praised the integration potential but reported bugs and fabricated outputs. Documentation warns the feature is powerful and dangerous, citing prompt injection and data-destruction risks.
Read at Theregister
Unable to calculate read time
Collection
[
|
...
]