add_knowledge_base_article
ChatGPTAdd a knowledge-base Article or Paragraph to an AI Agent (Paragraphs ignore the title). The article is embedded automatically in the background; no retrain step is needed. Requires EDITOR-or-above role.
Business
Overview
Quickchat AI connects ChatGPT to the AI Agents and customer conversations you manage in Quickchat. Sign in once with your Quickchat account and run your whole operation from ChatGPT. Analyze: week-over-week performance, resolution rate, CSAT, handoff reply times, top customer intents, and in-chat feedback across every channel your Agents run on (web chat, Slack, Telegram, Intercom, Zendesk, HubSpot, Meta, Instagram). Operate: search and read full conversation transcripts, surface flagged conversations and market insights, and export conversations to CSV/XLSX. Build: create a new AI Agent, auto-configure it from a website, add knowledge-base articles and update its persona without leaving ChatGPT. Every tool enforces the same per-Agent role checks as the Quickchat dashboard. Quickchat only accesses the Agents and conversations your own account can already reach.
Tools
add_knowledge_base_article
ChatGPTAdd a knowledge-base Article or Paragraph to an AI Agent (Paragraphs ignore the title). The article is embedded automatically in the background; no retrain step is needed. Requires EDITOR-or-above role.
add_knowledge_base_article
ChatGPTAdd a knowledge-base Article or Paragraph to an AI Agent (Paragraphs ignore the title). The article is embedded automatically in the background; no retrain step is needed. Requires EDITOR-or-above role.
compare_periods
ChatGPTCompare the analytics overview between two date ranges.
compare_periods
ChatGPTCompare the analytics overview between two date ranges.
compare_periods
ChatGPTCompare the analytics overview between two date ranges.
create_assistant
ChatGPTCreate a new AI Agent under your account, optionally with initial settings. Provisions a real AI Agent on the free tier (no charge) and returns its scenario_id, so you MUST pass confirm=true to avoid creating one by accident. Configure it with update_assistant_settings, add_knowledge_base_article, or onboard_assistant_from_url; knowledge-base changes are embedded automatically.
create_assistant
ChatGPTCreate a new AI Agent under your account, optionally with initial settings. Provisions a real AI Agent on the free tier (no charge) and returns its scenario_id, so you MUST pass confirm=true to avoid creating one by accident. Configure it with update_assistant_settings, add_knowledge_base_article, or onboard_assistant_from_url; knowledge-base changes are embedded automatically.
create_assistant
ChatGPTCreate a new AI Agent under your account, optionally with initial settings. Provisions a real AI Agent on the free tier (no charge) and returns its scenario_id, so you MUST pass confirm=true to avoid creating one by accident. Configure it with update_assistant_settings, add_knowledge_base_article, or onboard_assistant_from_url; knowledge-base changes are embedded automatically.
export_conversations
ChatGPTExport conversations to CSV/XLSX in a date range (max 31 days). Returns an EmbeddedResource pointing at a signed download URL that expires in 5 minutes. NOTE: this tool runs synchronously and can take 30+ seconds for high-volume chatbots — set the user's expectation accordingly before calling.
export_conversations
ChatGPTExport conversations to CSV/XLSX in a date range (max 31 days). Returns an EmbeddedResource pointing at a signed download URL that expires in 5 minutes. NOTE: this tool runs synchronously and can take 30+ seconds for high-volume chatbots — set the user's expectation accordingly before calling.
export_conversations
ChatGPTExport conversations to CSV/XLSX in a date range (max 31 days). Returns an EmbeddedResource pointing at a signed download URL that expires in 5 minutes. NOTE: this tool runs synchronously and can take 30+ seconds for high-volume chatbots — set the user's expectation accordingly before calling.
get_analytics_overview
ChatGPTAggregate analytics for an assistant over a date range — the right source for any count, total, average, rate, or trend, such as how many conversations or messages there were or how the chatbot is doing. Returns total conversations and total messages with daily, per-channel, per-language and per-hour breakdowns; total handoffs; and resolution metrics:
total_resolved (confirmed plus assumed resolutions, returned separately as total_confirmed_resolutions and total_assumed_resolutions), resolution_rate as a percentage of conversations, and a daily resolution_by_day breakdown; plus sentiment and topic trends and messages used vs the billing limit. Computed server-side over the whole range; it does not enumerate individual conversations.get_analytics_overview
ChatGPTAggregate analytics for an assistant over a date range — the right source for any count, total, average, rate, or trend, such as how many conversations or messages there were or how the chatbot is doing. Returns total conversations and total messages with daily, per-channel, per-language and per-hour breakdowns; total handoffs; and resolution metrics:
total_resolved (confirmed plus assumed resolutions, returned separately as total_confirmed_resolutions and total_assumed_resolutions), resolution_rate as a percentage of conversations, and a daily resolution_by_day breakdown; plus sentiment and topic trends and messages used vs the billing limit. Computed server-side over the whole range; it does not enumerate individual conversations.get_analytics_overview
ChatGPTAggregate analytics for an assistant over a date range — the right source for any count, total, average, rate, or trend, such as how many conversations or messages there were or how the chatbot is doing. Returns total conversations and total messages with daily, per-channel, per-language and per-hour breakdowns; total handoffs; and resolution metrics:
total_resolved (confirmed plus assumed resolutions, returned separately as total_confirmed_resolutions and total_assumed_resolutions), resolution_rate as a percentage of conversations, and a daily resolution_by_day breakdown; plus sentiment and topic trends and messages used vs the billing limit. Computed server-side over the whole range; it does not enumerate individual conversations.get_assistant_settings
ChatGPTRead an AI Agent's current persona/configuration and knowledge-base descriptions. Requires EDITOR-or-above role on the scenario (matches the dashboard settings page).
get_assistant_settings
ChatGPTRead an AI Agent's current persona/configuration and knowledge-base descriptions. Requires EDITOR-or-above role on the scenario (matches the dashboard settings page).
get_assistant_settings
ChatGPTRead an AI Agent's current persona/configuration and knowledge-base descriptions. Requires EDITOR-or-above role on the scenario (matches the dashboard settings page).
get_conversation_detail
ChatGPTFull transcript plus analysis for a single conversation. Hard-capped at 500 messages per call. If the conversation is longer, the response sets
meta.message_cap_reached: true and includes meta.next_from_ord; pass that as from_ord to fetch the next page.get_conversation_detail
ChatGPTFull transcript plus analysis for a single conversation. Hard-capped at 500 messages per call. If the conversation is longer, the response sets
meta.message_cap_reached: true and includes meta.next_from_ord; pass that as from_ord to fetch the next page.get_conversation_detail
ChatGPTFull transcript plus analysis for a single conversation. Hard-capped at 500 messages per call. If the conversation is longer, the response sets
meta.message_cap_reached: true and includes meta.next_from_ord; pass that as from_ord to fetch the next page.get_csat
ChatGPTCustomer Satisfaction (CSAT) ingested from external help-desk platforms (e.g. Zendesk, Intercom) on a 1-5 scale: total ratings, average_rating (1.0-5.0, null when none), the 1-5 distribution, and a daily series. Only present for Agents whose channels push CSAT, so an empty result means none was received, not low scores. Distinct from get_ratings (in-chat thumbs). Defaults to the last 30 days.
get_csat
ChatGPTCustomer Satisfaction (CSAT) ingested from external help-desk platforms (e.g. Zendesk, Intercom) on a 1-5 scale: total ratings, average_rating (1.0-5.0, null when none), the 1-5 distribution, and a daily series. Only present for Agents whose channels push CSAT, so an empty result means none was received, not low scores. Distinct from get_ratings (in-chat thumbs). Defaults to the last 30 days.
get_csat
ChatGPTCustomer Satisfaction (CSAT) ingested from external help-desk platforms (e.g. Zendesk, Intercom) on a 1-5 scale: total ratings, average_rating (1.0-5.0, null when none), the 1-5 distribution, and a daily series. Only present for Agents whose channels push CSAT, so an empty result means none was received, not low scores. Distinct from get_ratings (in-chat thumbs). Defaults to the last 30 days.
get_insights
ChatGPTConversations the AI flagged for human attention (is_flagged with a flag_reason: abuse, safety, compliance, legal, distress) and market insights (free-text business/product signals like competitor mentions or feature requests). insight_type selects flagged, market_insights, or all. NOTE: this is NOT date-filtered; it returns the most recent matches across all time. Page with the opaque
next_cursor (max 100 per call) and filter by conversation_timestamp yourself if you need a date window.get_insights
ChatGPTConversations the AI flagged for human attention (is_flagged with a flag_reason: abuse, safety, compliance, legal, distress) and market insights (free-text business/product signals like competitor mentions or feature requests). insight_type selects flagged, market_insights, or all. NOTE: this is NOT date-filtered; it returns the most recent matches across all time. Page with the opaque
next_cursor (max 100 per call) and filter by conversation_timestamp yourself if you need a date window.get_insights
ChatGPTConversations the AI flagged for human attention (is_flagged with a flag_reason: abuse, safety, compliance, legal, distress) and market insights (free-text business/product signals like competitor mentions or feature requests). insight_type selects flagged, market_insights, or all. NOTE: this is NOT date-filtered; it returns the most recent matches across all time. Page with the opaque
next_cursor (max 100 per call) and filter by conversation_timestamp yourself if you need a date window.get_ratings
ChatGPTIn-chat visitor feedback collected in the widget: thumbs/emoji answers to 'Was the AI helpful?' and 'How was your experience?', plus optional reasons. Returns raw counts per question and response, with no average score. Distinct from get_csat (external 1-5 CSAT). Defaults to the last 30 days.
get_ratings
ChatGPTIn-chat visitor feedback collected in the widget: thumbs/emoji answers to 'Was the AI helpful?' and 'How was your experience?', plus optional reasons. Returns raw counts per question and response, with no average score. Distinct from get_csat (external 1-5 CSAT). Defaults to the last 30 days.
get_ratings
ChatGPTIn-chat visitor feedback collected in the widget: thumbs/emoji answers to 'Was the AI helpful?' and 'How was your experience?', plus optional reasons. Returns raw counts per question and response, with no average score. Distinct from get_csat (external 1-5 CSAT). Defaults to the last 30 days.
get_topics
ChatGPTDistribution of customer INTENT across conversations in the date range, into seven fixed buckets: purchase, support, inquiry, complaint, feedback, subscription, other. Use for 'what are people contacting us about'. These are intent categories, not free-text topics. For free-text topic labels use the
topics_by_day field of get_analytics_overview. Defaults to the last 30 days; meta flags sampling on very large windows.get_topics
ChatGPTDistribution of customer INTENT across conversations in the date range, into seven fixed buckets: purchase, support, inquiry, complaint, feedback, subscription, other. Use for 'what are people contacting us about'. These are intent categories, not free-text topics. For free-text topic labels use the
topics_by_day field of get_analytics_overview. Defaults to the last 30 days; meta flags sampling on very large windows.get_topics
ChatGPTDistribution of customer INTENT across conversations in the date range, into seven fixed buckets: purchase, support, inquiry, complaint, feedback, subscription, other. Use for 'what are people contacting us about'. These are intent categories, not free-text topics. For free-text topic labels use the
topics_by_day field of get_analytics_overview. Defaults to the last 30 days; meta flags sampling on very large windows.get_ttfr
ChatGPTHow fast HUMAN agents send their first reply after a conversation is handed off to them, in wall-clock SECONDS (not minutes, not business-hours-adjusted, so overnight gaps inflate it). Returns average and median seconds, a daily series, and a per-agent breakdown. Measures human responders, NOT the AI's speed, and only covers handed-off conversations; prefer the median. Defaults to the last 30 days.
get_ttfr
ChatGPTHow fast HUMAN agents send their first reply after a conversation is handed off to them, in wall-clock SECONDS (not minutes, not business-hours-adjusted, so overnight gaps inflate it). Returns average and median seconds, a daily series, and a per-agent breakdown. Measures human responders, NOT the AI's speed, and only covers handed-off conversations; prefer the median. Defaults to the last 30 days.
get_ttfr
ChatGPTHow fast HUMAN agents send their first reply after a conversation is handed off to them, in wall-clock SECONDS (not minutes, not business-hours-adjusted, so overnight gaps inflate it). Returns average and median seconds, a daily series, and a per-agent breakdown. Measures human responders, NOT the AI's speed, and only covers handed-off conversations; prefer the median. Defaults to the last 30 days.
list_conversations
ChatGPTBrowse or find individual conversations in the Inbox, newest first, optionally filtered by channel, status, assignee, or a full-text query. Cursor-paginated via
next_cursor (do not increment a numeric offset), max 100 per page. This is for locating or reading specific conversations, NOT for counts or statistics — for totals, volume, resolution rate, or any aggregate over a period use get_analytics_overview instead. Cost guidance for high-volume chatbots: always pass start_date/end_date to constrain the result set. The full-text query parameter is bounded to messages from the date window; without explicit dates it defaults to the last 30 days. If the FTS subquery hits its 5000-message cap the response will set meta.fts_subquery_capped: true — in that case narrow the date range or refine the query.list_conversations
ChatGPTBrowse or find individual conversations in the Inbox, newest first, optionally filtered by channel, status, assignee, or a full-text query. Cursor-paginated via
next_cursor (do not increment a numeric offset), max 100 per page. This is for locating or reading specific conversations, NOT for counts or statistics — for totals, volume, resolution rate, or any aggregate over a period use get_analytics_overview instead. Cost guidance for high-volume chatbots: always pass start_date/end_date to constrain the result set. The full-text query parameter is bounded to messages from the date window; without explicit dates it defaults to the last 30 days. If the FTS subquery hits its 5000-message cap the response will set meta.fts_subquery_capped: true — in that case narrow the date range or refine the query.list_conversations
ChatGPTBrowse or find individual conversations in the Inbox, newest first, optionally filtered by channel, status, assignee, or a full-text query. Cursor-paginated via
next_cursor (do not increment a numeric offset), max 100 per page. This is for locating or reading specific conversations, NOT for counts or statistics — for totals, volume, resolution rate, or any aggregate over a period use get_analytics_overview instead. Cost guidance for high-volume chatbots: always pass start_date/end_date to constrain the result set. The full-text query parameter is bounded to messages from the date window; without explicit dates it defaults to the last 30 days. If the FTS subquery hits its 5000-message cap the response will set meta.fts_subquery_capped: true — in that case narrow the date range or refine the query.list_knowledge_base_articles
ChatGPTList knowledge base articles, most-recently-updated first. Cursor-paginated: use
next_cursor to fetch the next page. Returns up to limit items per call (max 100).list_knowledge_base_articles
ChatGPTList knowledge base articles, most-recently-updated first. Cursor-paginated: use
next_cursor to fetch the next page. Returns up to limit items per call (max 100).list_knowledge_base_articles
ChatGPTList knowledge base articles, most-recently-updated first. Cursor-paginated: use
next_cursor to fetch the next page. Returns up to limit items per call (max 100).list_scenarios
ChatGPTList all chatbots (scenarios) this connection can access. Returns scenario_id, chatbot name, and the user's role per scenario, so a chatbot named by the user can be resolved to its scenario_id.
list_scenarios
ChatGPTList all chatbots (scenarios) this connection can access. Returns scenario_id, chatbot name, and the user's role per scenario, so a chatbot named by the user can be resolved to its scenario_id.
list_scenarios
ChatGPTList all chatbots (scenarios) this connection can access. Returns scenario_id, chatbot name, and the user's role per scenario, so a chatbot named by the user can be resolved to its scenario_id.
onboard_assistant_from_url
ChatGPTAuto-configure an AI Agent from a website: scrapes the page, generates a full persona and settings, and embeds the content — all in the background (typically 20-60s). Returns immediately with status 'started'. This OVERWRITES the Agent's existing configuration, so it is best on a freshly created Agent. Requires EDITOR-or-above role.
onboard_assistant_from_url
ChatGPTAuto-configure an AI Agent from a website: scrapes the page, generates a full persona and settings, and embeds the content — all in the background (typically 20-60s). Returns immediately with status 'started'. This OVERWRITES the Agent's existing configuration, so it is best on a freshly created Agent. Requires EDITOR-or-above role.
onboard_assistant_from_url
ChatGPTAuto-configure an AI Agent from a website: scrapes the page, generates a full persona and settings, and embeds the content — all in the background (typically 20-60s). Returns immediately with status 'started'. This OVERWRITES the Agent's existing configuration, so it is best on a freshly created Agent. Requires EDITOR-or-above role.
submit_mcp_feedback
ChatGPTRecord feedback about this MCP for the Quickchat product team.
submit_mcp_feedback
ChatGPTRecord feedback about this MCP for the Quickchat product team.
submit_mcp_feedback
ChatGPTRecord feedback about this MCP for the Quickchat product team.
update_assistant_settings
ChatGPTUpdate an AI Agent's persona and configuration: personality (an enum id, see the field), profession, creativity_level, greeting(s), header(s), language, reply_length, and the knowledge-base one_word_description / short_description / ai_commands. Only the fields you pass change, and changes take effect immediately — no retrain needed. Requires EDITOR-or-above role on the scenario.
update_assistant_settings
ChatGPTUpdate an AI Agent's persona and configuration: personality (an enum id, see the field), profession, creativity_level, greeting(s), header(s), language, reply_length, and the knowledge-base one_word_description / short_description / ai_commands. Only the fields you pass change, and changes take effect immediately — no retrain needed. Requires EDITOR-or-above role on the scenario.
update_assistant_settings
ChatGPTUpdate an AI Agent's persona and configuration: personality (an enum id, see the field), profession, creativity_level, greeting(s), header(s), language, reply_length, and the knowledge-base one_word_description / short_description / ai_commands. Only the fields you pass change, and changes take effect immediately — no retrain needed. Requires EDITOR-or-above role on the scenario.
whoami
ChatGPTIdentify the dashboard user this MCP connection is authenticated as. Returns the user's email and the count of scenarios accessible. Use list_scenarios to enumerate the scenarios themselves.
whoami
ChatGPTIdentify the dashboard user this MCP connection is authenticated as. Returns the user's email and the count of scenarios accessible. Use list_scenarios to enumerate the scenarios themselves.
whoami
ChatGPTIdentify the dashboard user this MCP connection is authenticated as. Returns the user's email and the count of scenarios accessible. Use list_scenarios to enumerate the scenarios themselves.
Capabilities
Writes
