ChatGPT Plugin

Asking

AI-assisted customer support

Brand: Unknown

Category: Pending
Primary Subcategory: Pending

Integration details

Description

Run customer support with Asking, the shared inbox for your team, directly from ChatGPT and Codex. Requires an Asking account. This plugin connects your Asking workspace to your AI assistant so you can work on customer conversations without switching apps: - Search conversations, messages, contacts, and Help Center articles in one place. - Read a conversation with its full message history and contact details. - Draft replies for review, add private notes, and update status, priority, labels, and assignee. - Create and update Help Center articles. - Check report metrics for your account. It is designed for support and customer success teams that use Asking and want help triaging, summarizing, and answering customer conversations. Permissions and safety: every request runs with the permissions of the connected user. Read tools are available immediately; drafting, updating, and sending require the scopes you approve during connection. Sending a reply or starting a new conversation delivers a real message to the customer and requires the explicit send scope, which you can grant or revoke at any time. Limitations: the plugin cannot delete data, does not run bulk operations, and only sees the Asking account that authorized the connection.

Integration type: Plugin
Verification status: Not applicable
Platform: ChatGPT
Category: Pending
Primary Subcategory: Pending
Secondary Subcategories: None listed
Brand: Unknown
Access: Account required
First tracked: 2026-10-22
Tool count: 18
Geography: US

Agent DiscoverabilityChatGPT Plugin Discovery Score

ChatGPT organic discovery is live

Your score is coming

ChatGPT now suggests Plugins on its own when they match a user's request.Your Plugin Discovery Score measures how often yours appears, and it will show here as soon as it’s ready.

ChatGPT recommends Airtable when a user asks it to update a CRM. — ChatGPT surfaces Airtable because it matches the user's request.

Primary Subcategory

Competitive lineup

No Primary Subcategory assigned yetOnce Asking has a Primary Subcategory, the Plugins and Connectors it competes with will appear here with their scores.

Tools

18 tools agents can invoke

Add an internal private note to a conversation. Private notes are visible to agents in the dashboard only and are never sent to the customer.
add_private_note
Create a Help Center article in a portal. The article is saved as a draft unless status is explicitly published or archived.
create_article
Start a conversation with an existing contact in an accessible inbox and send the first message to the customer, in the name of the authorizing user. Requires the mcp:send scope. The contact must already exist (find it with search_contacts); channels that cannot start conversations return a clear error. Pass idempotency_key to make client retries safe: reusing the key returns the original conversation without creating a duplicate.
create_conversation
Save a reply draft for a conversation, like the dashboard composer draft. The draft is never sent to the customer; an agent has to send it from the dashboard.
create_draft
Read one Help Center article with its content. Read-only: use search_articles to find article IDs.
get_article
Read one contact with custom attributes, company and recent conversation history. Read-only: returns conversation display IDs for get_conversation.
get_contact
Read one conversation with its message history and contact details. Read-only; never sends anything to the customer.
get_conversation
Read-only report metrics for the current account, built from the same builders as the dashboard reports. report must be one of: account_summary, agent_summary, inbox_summary, team_summary, label_summary, channel_summary, first_response_time_distribution, outgoing_messages_count, csat_summary. since/until are Unix epoch seconds and default to the last 7 days. group_by only applies to outgoing_messages_count. agent_summary, team_summary and outgoing_messages_count grouped by agent or team require the report_rollup capability; csat_summary requires the csat capability and counts a response as satisfied when rating >= 4.
get_report
List agents in the current account so other tools can filter by assignee user ID.
list_agents
List active inboxes in the current account so other tools can filter by inbox ID.
list_inboxes
List teams in the current account so other tools can filter by team.
list_teams
Search Help Center articles in the current account, using semantic search when configured and keyword matching otherwise. Read-only: returns article IDs for get_article.
search_articles
Search contacts in the current account by name, email or phone number. Read-only: returns contact IDs for get_contact.
search_contacts
Search conversations in the current account, newest activity first. Read-only: returns conversation IDs for get_conversation.
search_conversations
Search conversations, messages, contacts and Help Center articles in one call. Conversations match contact name/email or display ID, messages match content, contacts match name/email/phone/identifier and articles match title/content. Read-only: returns the first page per type without cross-type pagination; use search_conversations, search_contacts or search_articles to go deeper.
search
Send a reply to the customer on an existing conversation, in the name of the authorizing user, like a reply sent from the dashboard. Sending is irreversible and requires the mcp:send scope. Pass idempotency_key to make client retries safe: reusing the key returns the original result without sending again.
send_reply
Update a Help Center article. The current publication state is kept unless status is explicitly provided.
update_article
Update reversible conversation metadata: status, priority, labels and assignee. Use none to clear the priority. Labels are added without removing existing ones. Does not send anything to the customer.
update_conversation

FAQs

Asking ChatGPT Plugin FAQ

How the directory, categories and Discoverability Score work.

Read the methodology

How do I improve Asking's ChatGPT Plugin discoverability?

The levers are the listing surface agents actually read: names, descriptions, keywords, tool metadata, and registry health. Which lever matters depends on where discovery breaks, which is what continuous measurement shows.

Where is this profile measured?

This profile uses the geography attached to the latest public registry snapshot: US. Locale tags are intentionally omitted.