Everything Claude can do on MyChatBot

Get the owner's DEMO PAGE — the live preview link for the agent built from their website at signup. THE ONLY WAY to show someone an existing demo. Call this FIRST in any new conversation, before asking the owner anything, AND every later time they ask for it, however they word it: 'show me the demo page', 'show me my demo', 'open my demo', 'where is my preview link', 'send me the link', 'do I have a chatbot?', 'show me my agent/bot', 'what did you build for me?'. Signup offers to build one from their website, so it often already exists: if it does, open with the preview link, because seeing their own agent answering questions about their own business is the fastest way to understand this product. NEVER answer 'show me the demo' with create_website_widget — that builds a SECOND, blank widget beside the demo they already have and shows them an empty page. Read-only.

Set up an AI chatbot that answers a business's customers automatically — on their website, Telegram, Instagram, Messenger or WhatsApp. Use this whenever someone wants a chatbot, an AI assistant, auto-replies, or 24/7 support for their shop, store, online business or service — including 'answer my customers', 'reply to my DMs', 'a bot for my website'. It renders an approval card the owner reviews before anything is built: draft the assistant first (research the business, then write the greeting, the instructions and the starter knowledge) and pass the whole proposal here. Nothing is created until the owner approves.

Build the assistant exactly as proposed. Called only after the owner approves the card.

Put a live chat widget on the owner's website — the chat bubble visitors click to ask questions. Use for 'add chat to my site', 'a chatbot on my website', 'live chat for my store', or putting an existing agent on a web page. The one channel that connects fully from here, no dashboard needed: returns a ready-to-paste embed snippet plus a hosted page URL so it can be dropped onto any site (or tried immediately on the hosted page). Idempotent: calling again with the same widget_id for the same assistant returns the existing widget's embed; a widget_id owned by a different assistant is refused. Omit widget_id to use the assistant's default widget — if signup already built a demo widget for this assistant, that one is returned rather than a second one created. NOT for showing an existing demo: 'show me the demo page' / 'show me my agent' / 'where is my preview link' are get_demo_status, which returns the page they already have. Creating one here instead leaves them looking at a blank page. The widget has many more settings than this tool takes — which details the contact form asks for (name/email/phone), button position and size, popup timing, margins. For any of those, give the owner the config_link from the result: it opens that widget's settings page and signs them in. Do not say it cannot be changed, and do not re-create the widget to try to change it.

Make the agent answer customers on Telegram — for 'connect my Telegram', 'a Telegram bot for my shop', or 'reply to Telegram messages automatically'. Completes here, no dashboard trip: ask the owner to open @BotFather in Telegram, run /newbot, and paste the token it gives them. Idempotent: reconnecting the same bot to the same assistant refreshes the token and turns it back on. This is a WRITE: it makes the assistant answer real people on Telegram. The token is a credential — never repeat it back in the conversation.

Get the dashboard link for connecting Telegram to an assistant. Prefer connect_telegram, which finishes the whole connection here; use this only if the owner would rather do it in the dashboard. so this returns a deep-link ({url}) for the owner to open in their browser — present it as "finish connecting in your dashboard (login required)". Read-only: this call connects and changes nothing by itself.

Get the dashboard link for connecting WhatsApp to an assistant. WhatsApp authorization can only be completed in the MyChatBot dashboard, so this returns a deep-link ({url}) for the owner to open in their browser — present it as "finish connecting in your dashboard (login required)". Read-only: this call connects and changes nothing by itself.

Get the dashboard link for connecting Instagram to an assistant. Instagram authorization can only be completed in the MyChatBot dashboard, so this returns a deep-link ({url}) for the owner to open in their browser — present it as "finish connecting in your dashboard (login required)". Read-only: this call connects and changes nothing by itself.

Let a sales agent take orders in conversation. Until this is on the agent can answer questions and recommend products but cannot close a sale — it has nowhere to record what the customer wants, so it hands off to a human instead. Turn it on once the catalog is imported. Safe to call again to change the settings; it will not create a second setup. Omit required_fields/item_fields to accept sensible defaults (name, phone, delivery address, optional email; quantity per item).

Stop a sales agent from taking orders. It keeps answering questions and recommending products, but can no longer record a sale. Existing orders are kept. If no other agent on the account takes orders, the order-form setup (fields, currency, payment rule) is removed with it — enabling again starts from defaults.

Disconnect one channel from an agent: the platform stops delivering and the connection is removed. Conversations are KEPT — the agent just stops getting new messages there. This is the right tool for 'take it off Telegram' or 'stop it answering on the website'. Use list_channels first to get the exact channel name.

Permanently delete a sales agent. THIS ALSO DELETES EVERY CONVERSATION IT HAS HAD WITH CUSTOMERS, plus its channels, skills and tasks. There is no undo and no export. Intended for removing an agent created by mistake — a duplicate from a repeated setup, say. If the agent has any conversations this call FAILS and tells you how many: relay that number to the owner and get an explicit yes before retrying with delete_conversations, never set it pre-emptively. When they only want the agent to stop working, use delete_channel instead — it keeps the history.

Teach the agent a business's website so it answers from the real pages — prices, products, delivery, opening hours, policies. Use for 'answer from my website', 'learn my site', 'use my shop's pages', or when the owner names a site as their source of truth. It is a LIVE source: the agent searches the site and reads pages at answer time, so there is nothing to upload and no indexing wait. The knowledge_base group name links sources to assistants; assistants without a knowledge base yet are attached to this group automatically.

Create a new FAQ knowledge base integration for the owner's assistant. Optionally seed it with initial entries. Each entry needs an id, question (short title), and answer (detailed text). The knowledge_base param groups integrations — use an existing group name to add to that group, or pick a new unique name. Check list_integrations first and prefer updating an existing FAQ integration over creating a duplicate.

List all entries in a FAQ knowledge base integration. Returns the full list of FAQ items with their IDs, questions, and answers. Omit integration_id when the account has only one FAQ — it is resolved for you; with several, the error names them. Note that a 'Site link' integration is NOT an FAQ knowledge base even though list_integrations marks both as knowledge bases — passing its id here fails.

Modify entries in a FAQ knowledge base. Supports three granular operations (use any combination): add (new entries to append, or replace one with the same id), update (existing entries to change, matched by id), remove (entry IDs to delete). The backend reads the current entries, applies your changes, re-uploads, and re-indexes.

Create a Products integration — a manually-managed product catalog the assistant answers from. Optionally seed with initial products. Each product can have arbitrary attributes (name, description, price, url, image_url, category, and any custom keys). Processing is asynchronous — returns immediately while indexing happens in the background; check status with get_integration. Check list_integrations first and prefer one catalog per account over duplicates.

List the products in a catalog. Omit integration_id to be answered for the account as a whole: one catalog is opened directly, several come back as a list of catalogs with each one's live counts, and none says so. A manual Products catalog and a Product Spreadsheet (a connected Google Sheet) return a page of products — read a large one a page at a time by passing next_offset back as offset. A Product Feed is indexed for search rather than stored as a list, so it reports live counts and its source feed URL rather than items; every response says which kind it is in type, and whether it can be paged in products_listable. Note that a 'Site link' integration is NOT a product catalog even though list_integrations marks both as knowledge bases — passing its id here fails.

Modify products in a Products integration. Supports three granular operations (use any combination): add (new products to append; each must have 'name', other keys are arbitrary), update (existing products to change, matched by id, merges provided fields), remove (product IDs to delete). The backend reads current products, applies changes, re-uploads, and re-indexes.

Create a Product Feed integration that indexes products from a feed URL for semantic search. Supports JSON, XML, Google Shopping, YML, and similar feed formats. Processing is asynchronous — returns immediately while indexing happens in the background. Use get_integration(integration_id) to check processing status.

List all integrations for this account: CRMs, knowledge bases, MCPs, automations. Supports filtering by type. Use this to find existing FAQ knowledge bases and product catalogs before creating new ones.

Get detailed info about a specific integration including metadata and configuration (sensitive fields stripped). Also the way to check async indexing status after creating or updating a catalog or feed.

Permanently delete an FAQ knowledge base and everything the agent learned from it. Cannot be undone — the answers are gone and the agent stops using them immediately. Use list_integrations first and confirm which one with the owner by name; ids are not interchangeable and this refuses anything that is not an FAQ.

Permanently delete a manually-added products catalog and everything indexed from it. Cannot be undone. This is for catalogs whose products were added by hand — for one imported from a feed URL use delete_product_feed_integration. Each refuses the other's type, so check with list_integrations first.

Permanently delete a product feed (a catalog imported from a feed URL) and everything indexed from it. Cannot be undone, and it stops the feed being re-imported. For a hand-built catalog use delete_products_integration instead — each refuses the other's type.

Business pulse for a period on the connected MyChatBot account: total orders, active chats, new clients, and LLM activity (requests + tokens). Both dates are optional — omit them for the upstream default period. Read-only. The response may include an `errors` map when a sub-source failed to load — treat that counter as unavailable, never as zero; retrying with a narrower date range usually helps.

Order statistics for the connected account over an optional period: total orders, total revenue, and breakdowns by channel and by status. Revenue is in the shop's own currency and is NOT normalized — present it as a bare number without inventing a currency symbol. Read-only.

List orders on the connected account with optional filters: period, client, status (pending, awaiting_payment, paid, in_progress, completed, cancelled), source channel, order reference, assistant. Offset pagination, applied after filtering: limit ≤ 200 (default 50), and the response's `total` is the filtered count before pagination while `count` is the rows returned. Read-only.

List recent chats sorted by last_active descending (most recent first), max 100 per call. Returns {chats: [...], count, next_last_active_before, next_before_id}. To page through more chats, pass next_last_active_before as last_active_before AND next_before_id as before_id from the previous response, then call again (keyset pagination); repeat until fewer than `limit` rows come back. Always pass BOTH cursor fields — next_last_active_before carries full sub-second precision (unlike the seconds-precision last_active shown on each chat), and next_before_id keeps paging exact when many chats share one timestamp. There is no offset parameter. Combine last_active_after and last_active_before to fetch a specific date window. Both accept RFC3339 timestamps (fractional seconds allowed) or date-only YYYY-MM-DD; a date-only value always means UTC start of day (00:00), so for the window 2026-07-25..2026-07-31 inclusive pass last_active_after=2026-07-25 and last_active_before=2026-08-01. Shows client name, channel, last active, unread count, and whether operator is needed. A chat with communication_channel="Calls" represents a phone call — its message history is the call transcript (use get_chat_messages). Every filter is optional; omit a field to include all values for it.

Get detailed info about a specific chat including metadata, follow-up state, and channel info. chat_id is the small integer `id` returned by list_chats — not page_id, not common_client_id, not any channel-specific external id. The response distinguishes three ids: `id` (the canonical chat id), `client_id` (per-channel external id), and `common_client_id` (the unified client UUID = clients.id); these are three different values, do not conflate them.

Read the message history of a specific chat. Returns the last N messages with role, content, and timestamp. For chats with communication_channel="Calls", the message history is the call transcript — there is no separate transcript endpoint.

List clients (leads/customers) with filtering by funnel status, labels, search, and pagination.

Get detailed info about a specific client (lead/customer) including contact info, funnel status, labels, and metadata. The response includes metadata.client_context — a map of custom fields collected from the client (only populated when the assistant has 'Client Context' enabled). Cross-reference the keys with the assistant's client_context_schema to render human-readable labels.

Check which plan the account is on and how many AI replies are left. Use this when the owner asks what they are paying for, how much trial they have left, or why their agent stopped answering. Read-only.

No parameters.

Get the link for subscribing or moving up a plan, along with what the account is on now and how many replies remain. Use it when a trial is running low, when the owner asks how to keep their agent running, or when they ask what it costs. Present the Solo plan as the natural next step for one agent on one channel ($19/month, 200 replies) and mention that bigger plans exist for more channels or volume. Read-only: it returns a link, it never charges anything. Always show the owner the URL itself, as a link they can click.

No parameters.

List all active sales agents (assistants) for this account. Returns id, name, status, language, and model. Use it to resolve the assistant_id that send_one_off_message and the outreach campaigns require.

No parameters.

List all connected channels (Telegram, WhatsApp, Instagram, Email, etc.) with their status; sensitive credentials are stripped. Use it to see what's connected before sending a message or launching a campaign — the communication_channel for send_one_off_message and the outreach_channels for a campaign come from here.

Send a single ad-hoc message to a specific lead through any connected non-Calls channel (WhatsApp, Telegram, Email, Instagram, Viber, etc.). Use for operator-style 'remind John about his appointment' situations. For multi-recipient campaigns use immediate_outreach_create. The message is written to the lead's chat history just like a normal reply, so it shows up in the chat panel. Always confirm the recipient, channel, and message with the owner before sending — messages are real and immediate. If unsure which channel to use, call list_channels first.

Preview how many clients match a campaign's filters WITHOUT creating anything. Read-only — always run this before immediate_outreach_create so the owner knows how many people a campaign would reach.

Create and schedule an immediate outreach campaign to many leads at once. Returns the matched audience count. ALWAYS run immediate_outreach_preview_audience first and confirm the audience size, channels, and message with the owner before creating — a campaign sends real messages to real customers.

Pause, resume, or reset an immediate outreach campaign. Use 'user_paused' to pause, 'scheduled' to resume, 'draft' to reset (clears all progress and stats).

List follow-up automations (outreach campaigns). Supports filtering by type and status.

Get detailed info about a follow-up (outreach campaign) including steps, filters, and execution stats.

Start a test chat session with an assistant to try it from right here, before (or without) putting it in front of customers. The assistant_id is the session key — one test session per assistant — and starting clears any previous test chat history. Test chats are free: rehearsal replies do not spend the account's token balance.

Send a message in the assistant's test chat session and get its reply. Synchronous: waits for the full model response, generated from the assistant's current LIVE instructions and skills. Test replies are free — they do not spend the account's token balance (changed 2026-07-28; they used to bill a full message each). When the ACCOUNT balance runs low — which live customer replies do consume — a clearly-marked trial_warning line is appended below the reply.

End the assistant's test chat session and clear its history. The assistant_id is the session key. Call this when a test conversation is done — a later test_chat_start also starts clean.

Render a review card for changing an assistant's instructions (system prompt): fetches the CURRENT instructions and shows them next to your PROPOSED replacement so the owner can compare before anything happens. NOTHING is saved by this call — the card's Confirm button performs the update (via update_assistant_instructions), same rule as the setup flow: nothing changes until the owner says so. This is the recommended path for every instructions edit. The proposed text must be the COMPLETE new instructions (full replacement, not a diff).

Replace an assistant's instructions (system prompt) with new text — the WRITE behind propose_instructions_update's Confirm button. The card is the recommended path (propose first, let the owner confirm); call this directly only when the owner has already approved the exact text in conversation. Full replacement; the platform runs a moderation check before saving and rejects flagged content.