Pulls bot transcripts and usage figures, clones blueprints into new bots, resyncs training datasets, and wires up messaging channels.
284actions available
Every action runs live through MCP. Nothing to build, nothing to maintain.
Ayro adds multiple customer messages to a conversation at once, bulk-loading transcripts or threads efficiently. This saves time when importing conversation histories.
Ayro stores files within ChatBotKit conversations so the AI bot can reference documents, receipts, or images during exchanges. This provides context for smarter responses.
Ayro converts text responses into natural speech audio, letting customers hear answers instead of reading text. This supports multimodal and accessibility-focused interactions.
Each card is one request a support team gets, and the Chatbotkit actions Ayro runs to close it.
Ayro lists recent conversations, opens one with its full message history, and reports the token usage that thread consumed, so a complaint about a bad answer is investigated against the real transcript.
Ayro clones a blueprint that already carries your prompt and model settings, creates the bot from it, and opens a session so the new bot can be tried immediately rather than configured field by field.
Ayro re-crawls the sitemap behind a dataset, resyncs an attached file, and edits an individual record when a single fact changed, so answers track the source instead of drifting from it.
Ayro invokes a trigger integration when something happens elsewhere, runs the task attached to it, and publishes the result into the subscribed channel so the bot reacts without anyone opening it.
How it works
Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Ayro reads the Chatbotkit actions it has and picks the ones a request needs.
Authorize the Chatbotkit account your team already uses — one consent screen, no API keys, no mapping tables. Ayro can only do what you granted that account, and you can disconnect it at any time.
Describe the job the way you would hand it to a teammate. Ayro maps it to the Chatbotkit actions that close it and chains as many as the request needs.
The agent runs the actions inside the conversation the customer is already in, so nobody copies data between tabs and your team can take over at any point.
Get started freeChatbotkit · Ayro
What can you do in Chatbotkit without me setting anything up?
These, right away:
Great, let's start with the first one.
FAQ
Setup, permissions, and the limits of what Ayro can do inside Chatbotkit.
ChatBotKit exposes both a REST and a GraphQL API and the toolkit mirrors both, so Create Bot and Create Bot (GraphQL) reach the same object by different routes. There is also a general Execute GraphQL Query action for shapes the named actions do not cover, which is the escape hatch for a read that needs several related records at once.
All 284 actions your agent can call on Chatbotkit, straight from the live MCP connection.
Attach a file to a dataset as a source.
Authenticate a secret by its ID.
Clone an existing blueprint.
Clone an existing bot.
Clone a platform example.
Clone an existing widget integration.
Send a message to a ChatBotKit conversation and receive the bot's AI-generated reply.
Create a new blueprint in ChatBotKit.
Create a new blueprint template via GraphQL mutation.
Create a new AI bot with configurable settings.
Create a new bot using GraphQL mutation.
Creates a new bot session with an associated conversation and authentication token.
Create a new contact.
Create a new conversation.
Create a new message in an existing conversation.
Create multiple messages in a conversation in a single batch operation.
Create a new conversation session with an authentication token.
Create a new dataset using GraphQL mutation.
Create a new record in a dataset.
Create a Discord integration for a ChatBotKit bot.
Create a new email integration for a ChatBotKit bot.
Create a new Extract integration for a ChatBotKit bot.
Create a new file resource in ChatBotKit.
Create an Instagram integration for a ChatBotKit bot.
Creates a new support integration for a ChatBotKit bot.
Create a new MCP Server integration for ChatBotKit.
Create a new memory entry.
Create a Facebook Messenger integration for a ChatBotKit bot.
Create a Notion integration for a ChatBotKit dataset.
Create a rating in ChatBotKit.
Same connection, same setup. Pick the next one your team already uses.
Starts cloud browser tasks, polls their progress step by step, kills a stuck run and fetches the files a task produced.
Clones and updates chatflows, rewrites document store chunks behind bad answers, reads collected leads and feedback, and health-checks the instance.
Creates and reconfigures pipes, manages retrieval memories and threads, and pulls execution traces when a run needs debugging.
Runs similarity searches and reranks results, upserts records with generated embeddings, provisions indexes and namespaces, and runs backups and imports.
Reports Stack AI health and license status, lists available providers, actions, and triggers, and returns the schema each one expects.
Queries a knowledge graph for grounded answers, uploads and indexes new documents into it, and unlinks the files that have gone out of date.

Authorize the account and your agent has all 284 actions from the first conversation.
