Skip to content
HomeNewsDigestsConceptsGuidesToolbox
AboutSubscribeUA
Subscribe

AI Today Brief

The daily AI-engineering brief. Built in public. EN · UA.

XTelegramLinkedInYouTubeRSS

Follow AI Today Brief on LinkedIn for daily AI-engineering updates and the weekly “5 shifts that changed how developers work” PDF.

Explore

NewsDigestsConceptsGuides

Company

SubscribeAdvertiseAbout

Legal

Editorial policyAI disclosurePrivacyTerms

© 2026 AI Today Brief. All rights reserved.

  1. Home/
  2. News/
  3. Agents & MCP/
  4. ChatGPT Plugins Support Multi-Account Authentication with Model Context Protocol Profile Tools
Agents & MCP

ChatGPT Plugins Support Multi-Account Authentication with Model Context Protocol Profile Tools

OpenAI updated ChatGPT plugins to allow users to connect multiple accounts simultaneously within the same chat session. Developers building Model Context Protocol servers can integrate a profile tool to ensure ChatGPT clearly differentiates and labels each account.

September 19, 2026· 5 min read
OKCurated by Oleksandr Kuzmenko, AI Product Engineer·Updated September 19, 2026·Sources cited on every story
AI-assisted · editor-reviewed·How we use AI
ChatGPT Plugins Support Multi-Account Authentication with Model Context Protocol Profile Tools

Impact: Medium

Why it matters

You can seamlessly bridge personal and work accounts in ChatGPT, while MCP server developers can structure multi-tenant profile metadata.

TL;DR

  • 01Enables simultaneous multi-account connections inside ChatGPT conversations.
  • 02Works out of the box for existing plugins with zero code changes required.
  • 03Adding a profile tool to MCP servers allows ChatGPT to explicitly label active accounts.

Key facts

Feature
Multi-account plugin connection
Developer Requirement
Works automatically; profile tool optional for custom labeling
Protocol
Model Context Protocol (MCP)

Unified Multi-Tenant Context

OpenAI has deployed multi-account authentication for plugins and integrations within ChatGPT. Users can now link multiple accounts from the same provider (for example, separate personal and organizational accounts) through the plugin directory (chatgpt.com/plugins). This capability allows the model to aggregate data across divergent authentication boundaries in a single chat thread.

Model Context Protocol Integration Guidelines

For existing plugins and tools, the change operates automatically without requiring breaking configuration updates. However, to optimize agent execution and avoid ambiguous tool dispatches, developers should explicitly declare profile discovery in their tool definitions:

  • Expose Profile Tools: Add a dedicated profile discovery tool to your Model Context Protocol (MCP) server according to the OpenAI plugin specification (developers.openai.com/plugins/build/).
  • Explicit Labeling: Providing structured profile metadata allows ChatGPT to inspect active accounts and display user-facing account labels during tool execution, ensuring users know exactly which identity an action modifies.

✓ When to use

  • Building MCP servers and plugins that interact with services where users manage both personal and corporate identities.
  • Connecting ChatGPT workflows across separate enterprise and personal environments in a unified conversation.

✕ When NOT to use

  • Services using single static API keys or anonymous public endpoints.
  • Workflows with strict organizational data isolation policies prohibiting shared multi-account sessions.

What to do today

  • →Navigate to chatgpt.com/plugins to connect secondary personal or team accounts.
  • →Add a profile tool to your custom MCP servers to support account labeling in ChatGPT.
#ChatGPT#Model Context Protocol

Sources

  • Max Stoiber on ChatGPT Multi-Account Plugins
ShareShare on XShare on LinkedIn
← Previous storyTypeSafe AI Launches Jev Probability Model for Fast Non-Hallucinating Agent WorkflowsNext story →Claude Code Adds AGENTS.md Support and Free Server-Side Auto Mode

Related stories

  • Agents & MCPAirport Manages Multiple Coding Agent Terminals Concurrently in Visual Studio Code
  • Agents & MCPHardening Agent Sandboxes After Gemini Test Breakout Breaches External Systems
  • Agents & MCPMnemosyne Adds Local Memory Quickstart for Hermes Agent Workflows
  • Agents & MCPGoogle Labs Deploys CC Multi-User Agent Harness on Isolated Cloud Environments

Email digest

Get the morning AI brief

One email a day — the stories that matter for engineers, founders and tech leads. Human-edited, with links to primary sources.

  • ✓120+ sources scanned daily
  • ✓Edited by a human
  • ✓1 email per day
  • ✓EN + UA

By subscribing you agree to the privacy policy.