[No QA] Update ChatGPT MCP connection doc for official connector directory

[marcaaron]

Explanation of Change

Expensify MCP is now in the official ChatGPT connector directory, so the old setup no longer applies. Previously users had to enable developer mode and manually create a connector by entering a URL and description. Now they just go to Settings > Plugins, find Expensify, and hit Connect.

Removed the developer mode section and manual "Create App" steps. Updated "How to connect" and "Who can connect" to reflect the Plugins flow.

Fixed Issues

No issue in particular. We were approved and in the official connectors directory now.

Tests

• Verify that no errors appear in the JS console

Offline tests

N/A — docs change

QA Steps

N/A — docs only

PR Author Checklist

• I linked the correct issue in the ### Fixed Issues section above
• I wrote clear testing steps that cover the changes made in this PR
  • I added steps for local testing in the Tests section
  • I added steps for the expected offline behavior in the Offline steps section
  • I added steps for Staging and/or Production testing in the QA steps section
  • I added steps to cover failure scenarios (i.e. verify an input displays the correct error message if the entered data is not correct)
  • I turned off my network connection and tested it while offline to ensure it matches the expected behavior (i.e. verify the default avatar icon is displayed if app is offline)
  • I tested this PR with a High Traffic account against the staging or production API to ensure there are no regressions (e.g. long loading states that impact usability).
• I included screenshots or videos for tests on all platforms
• I ran the tests on all platforms & verified they passed on:
  • Android: Native
  • Android: mWeb Chrome
  • iOS: Native
  • iOS: mWeb Safari
  • MacOS: Chrome / Safari
• I verified there are no console errors (if there's a console error not related to the PR, report it or open an issue for it to be fixed)
• I followed proper code patterns (see Reviewing the code)
  • I verified that comments were added to code that is not self explanatory
  • I verified that any new or modified comments were clear, correct English, and explained "why" the code was doing something instead of only explaining "what" the code was doing.
  • I verified any copy / text that was added to the app is grammatically correct in English. It adheres to proper capitalization guidelines (note: only the first word of header/labels should be capitalized), and is either coming verbatim from figma or has been approved by marketing (in order to get marketing approval, ask the Bug Zero team member to add the Waiting for copy label to the issue)
• If a new code pattern is added I verified it was agreed to be used by multiple Expensify engineers
• I followed the guidelines as stated in the Review Guidelines
• I tested other components that can be impacted by my changes (i.e. if the PR modifies a shared library or component like Avatar, I verified the components using Avatar are working as expected)
• If a new CSS style is added I verified that:
  • A similar style doesn't already exist
  • The style can't be created with an existing StyleUtils function (i.e. StyleUtils.getBackgroundAndBorderStyle(theme.componentBG))
• If new assets were added or existing ones were modified, I verified that:
  • The assets are optimized and compressed (for SVG files, run npm run compress-svg)
  • The assets load correctly across all supported platforms.
• If the PR modifies code that runs when editing or sending messages, I tested and verified there is no unexpected behavior for all supported markdown - URLs, single line code, code blocks, quotes, headings, bold, strikethrough, and italic.
• If the PR modifies a generic component, I tested and verified that those changes do not break usages of that component in the rest of the App (i.e. if a shared library or component like Avatar is modified, I verified that Avatar is working as expected in all cases)
• If the PR modifies a component or page that can be accessed by a direct deeplink, I verified that the code functions as expected when the deeplink is used - from a logged in and logged out account.
• If the PR modifies the UI (e.g. new buttons, new UI components, changing the padding/spacing/sizing, moving components, etc) or modifies the form input styles:
  • I verified that all the inputs inside a form are aligned with each other.
  • I added Design label and/or tagged @Expensify/design so the design team can review the changes.
• I added unit tests for any new feature or bug fix in this PR to help automatically prevent regressions in this user flow.
• If the main branch was merged into this PR after a review, I tested again and verified the outcome was still expected according to the Test steps.

Screenshots/Videos

Android: Native

N/A

Android: mWeb Chrome

N/A

iOS: Native

N/A

iOS: mWeb Safari

N/A

MacOS: Chrome / Safari

N/A

[github-actions]

Prohibited/vague navigation phrasing: Per HELPSITE_NAMING_CONVENTIONS.md (Prohibited Language and Deterministic Writing Rule), avoid "Find" for locating UI elements. Use a literal action referencing the exact label, e.g. 4. Select **Expensify** from the list.

[MelvinBot]

Done — replaced the vague "Find" with a literal action: 4. Select **Expensify** from the list. in Connect-ChatGPT-to-Expensify-Using-MCP.md:34.

[github-actions]

UI label inconsistency: This step now routes through Plugins, but the article's FAQ (Settings > Apps, Enabled Apps) still describes the connector as living under Apps. Use one exact tab/section label consistently throughout the article so the navigation matches the real UI (Core UI Referencing Rules).

[MelvinBot]

Done — made the tab/section label consistent throughout. The FAQ now uses Plugins / Enabled Plugins to match the updated connect flow (Settings > Plugins) at Connect-ChatGPT-to-Expensify-Using-MCP.md:79.

I aligned to Plugins since that's the label used in the new connect steps. If ChatGPT's actual UI label is Apps (or Connectors), flip both sections to that instead.

[github-actions]

HelpDot Documentation Review — see full review below.

Overall Assessment: This PR updates Connect-ChatGPT-to-Expensify-Using-MCP.md to reflect that Expensify is now in the official ChatGPT connector directory. It removes the developer mode and manual Create App connector sections and replaces them with a single How to connect Expensify in ChatGPT section (Settings > Plugins > Expensify > Connect). It also updates the Who can connect section and fixes a curly apostrophe. The changes are net simplifications and are well-aligned with the authoring guidelines.

Scores Summary:

• Readability: 9/10 — Streamlined flow; a single sequential connect procedure replaces two overlapping ones. Steps are clear, action-oriented, and correctly numbered.
• AI Readiness: 8/10 — New heading How to connect Expensify in ChatGPT is task-based, starts with How to, and includes the feature name. YAML metadata (including internalScope) and heading hierarchy remain intact.
• Style Compliance: 7/10 — Button and tab names are bold and in Sentence case, and the three dots reference is correct. One consistency issue introduced by the change (see below).

Key Findings:

• Positive: Removing developer mode and manual Create App steps materially reduces friction and matches the new official connector flow. Fewer, clearer steps.
• Positive: Curly apostrophe fixed to a straight apostrophe in the FAQ heading, and create it again changed to add it again reads more naturally for a directory connector.
• Consistency issue: The new steps navigate via Settings > Plugins, but the unchanged FAQ still references Settings > Apps and Enabled Apps. This leaves the article internally inconsistent about whether the location is Plugins or Apps. Confirm the exact UI label and align both, per the Core UI Referencing Rules (use exact UI text, no synonyms or generalization).
• Minor: The removed link to the ChatGPT Developer mode docs was an external full URL; its removal is a small side-benefit given the link-formatting guidance.

Recommendations:

• Priority: Verify the actual ChatGPT UI label (Plugins vs Apps) and make the connect steps and the FAQ use the same exact term. If the UI is now Plugins, update the FAQ lines referencing Apps and Enabled Apps to match.
• Suggestion: Confirm the Who can connect requirement wording (A ChatGPT account) reflects any remaining prerequisites, for example a paid tier, if the connector directory is gated.

Files Reviewed:

• docs/articles/new-expensify/connections/connect-ai-assistants/Connect-ChatGPT-to-Expensify-Using-MCP.md — Approved with a minor consistency fix recommended (Plugins vs Apps terminology alignment).

Note: Detailed line-by-line feedback has been provided as inline comments.

[marcaaron]

@MelvinBot can you make the requested changes?

[MelvinBot]

Made the two requested changes and pushed to marcaaron-update-chatgpt-mcp-connect-docs (7d7422a):

1. Vague navigation — 4. Find **Expensify** in the list. → 4. Select **Expensify** from the list. (literal action per HELPSITE_NAMING_CONVENTIONS.md).
2. Label inconsistency — the FAQ's leftover Settings > Apps / Enabled Apps references now read Settings > Plugins / Enabled Plugins, matching the updated connect flow so one label is used throughout.

⚠️ One thing to confirm: I aligned to Plugins because that's the label your new connect steps use. If ChatGPT's actual UI section is Apps (or Connectors), let me know and I'll flip both sections to that instead.

[OSBotify]

A preview of your ExpensifyHelp changes have been deployed to https://51a73ab8.helpdot.pages.dev ⚡️

Updated articles:

• articles/new-expensify/connections/connect-ai-assistants/Connect-ChatGPT-to-Expensify-Using-MCP