Integration

Chatling integration

Chatling builds AI chatbots trained on your own content. With this API an agent can list, create, duplicate and rename chatbots, ask a chatbot's knowledge-base AI a question (each answer consumes AI credits), add links, texts and FAQs to a chatbot's knowledge base and resync or delete them, list, create, read and delete the contacts and leads a chatbot captured (personal data), read, archive, flag and delete conversations and rate AI answers, and read the project's settings, members and usage (AI credits, email credits, chatbots, knowledge-base characters, seats). Building chatbot flows and AI settings is done in the Chatling app; the API has no route for it. Rate limit: 300 calls per minute per API key. Authentication is an API key created in the Chatling Project Settings, API Keys tab, sent as a Bearer token.

Connect Chatling How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Chatling.Built from the 33 Chatling tools below, on the connection you add once.

What you can do with Chatling

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Data source, 6 operations

add_faq_sourcesAdd faq sourcesPOSTAdds question and answer pairs (FAQs) to a chatbot's knowledge base and returns how many were added.
add_link_sourcesAdd link sourcesPOSTAdds webpages to a chatbot's knowledge base, optionally leaving out parts of each page; returns how many links were added and the duplicates removed.
add_text_sourcesAdd text sourcesPOSTAdds pieces of text to a chatbot's knowledge base and returns how many were added.
delete_data_sourceDelete data sourceDELETEDeletes a data source from a chatbot's knowledge base.
list_data_sourcesList data sourcesGETLists the data sources in a chatbot's knowledge base (type, processing status, characters used, resync state), one page at a time, optionally of one type.
resync_data_sourceResync data sourcePOSTResyncs a knowledge-base data source, queueing it to be processed again (list_data_sources shows resync_queued while it waits).

Chatbot, 5 operations

create_chatbotCreate chatbotPOSTCreates a chatbot in the project, from a template (template_id from list_chatbot_templates) or from scratch, and returns it with its new id.
duplicate_chatbotDuplicate chatbotPOSTCreates a copy of a chatbot in the project and returns the new chatbot's id.
get_chatbotGet chatbotGETReturns one chatbot of the project: id, name, version, visibility (public or private) and creation date.
list_chatbotsList chatbotsGETLists the chatbots of the project, one page at a time, each with its id, name, version, visibility (public or private) and creation date.
update_chatbot_settingsUpdate chatbot settingsPATCHRenames a chatbot or changes its visibility (public or private), and returns it. Leave out a field to keep its current value.

Contact, 4 operations

create_contactCreate contactPOSTCreates a contact for a chatbot from the details given (at least one of them) and returns its id. A Chatling workflow with a Contact created trigger then runs.
delete_contactDelete contactDELETEDeletes a contact from a chatbot.
get_contactGet contactGETReturns one contact of a chatbot: name, email, phone, job title, company, website and creation date. Personal data.
list_contactsList contactsGETLists the contacts and leads a chatbot saved (name, email, phone, job title, company, website, creation date), one page at a time. Personal data.

Conversation, 4 operations

delete_conversationDelete conversationDELETEDeletes a conversation of a chatbot.
get_conversationGet conversationGETReturns one conversation: contact id, archived and important flags, creation date and its last 20 messages with their role, text, AI sources and rating.
list_conversationsList conversationsGETLists a chatbot's conversations with users (contact id, archived and important flags, date) with each one's last 20 messages. Paginated by cursor: pass pages.next_cursor back as cursor.
update_conversationUpdate conversationPATCHArchives or unarchives a conversation, flags it as important or not, or links it to a contact (send at least one field); returns the conversation. Can start workflows with conversation update triggers.

Ai answer, 2 operations

chat_with_knowledge_baseChat with knowledge basePOSTAsks a chatbot's knowledge-base AI a question and returns its answer, its sources and the conversation id to continue the thread. Consumes AI credits (see list_ai_models).
rate_ai_answerRate ai answerPATCHRates a knowledge-base AI answer in a conversation as helpful (1) or not helpful (-1), or removes the rating (0). Only AI answers generated from the knowledge base can be rated.

Project settings, 2 operations

get_project_settingsGet project settingsGETReturns the project's id and name.
update_project_settingsUpdate project settingsPATCHRenames the project and returns its id and new name.

Ai credit usage, 1 operation

get_ai_credits_usageGet ai credits usageGETReturns the number of AI credits the project used and the maximum allowed for the project.

Ai language, 1 operation

list_ai_languagesList ai languagesGETLists the languages the knowledge-base AI can answer in (id and name); pass an id as language_id to chat_with_knowledge_base.

Ai model, 1 operation

list_ai_modelsList ai modelsGETLists the AI models a chatbot can answer with: id (for chat_with_knowledge_base), name, AI credits consumed per answer and the allowed temperature range.

Chatbot template, 1 operation

list_chatbot_templatesList chatbot templatesGETLists Chatling's chatbot templates (id, name, description), one page at a time; pass a template id to create_chatbot to start from it.

Chatbot usage, 1 operation

get_chatbots_usageGet chatbots usageGETReturns the number of chatbots created in the project and the maximum allowed for the project.

Email credit usage, 1 operation

get_email_credits_usageGet email credits usageGETReturns the number of email credits the project used and the maximum allowed for the project.

Knowledge base usage, 1 operation

get_knowledge_base_usageGet knowledge base usageGETReturns the number of knowledge-base characters the project uses and the maximum allowed for the project.

Member, 1 operation

list_membersList membersGETLists the members of the project with their email address, status (Active or Pending) and roles, one page at a time. Personal data.

Message, 1 operation

list_conversation_messagesList conversation messagesGETLists every message of a conversation, one page at a time: role (bot, user or system), text, whether it is a knowledge-base AI answer, its sources and rating.

User seat usage, 1 operation

get_user_seats_usageGet user seats usageGETReturns the number of user seats used in the project and the maximum allowed for the project.

Use Chatling from Claude Code, Cursor or Codex

Connect Chatling in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Chatling operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Chatling

Create your workspace
Sign up free. Nothing to install.
Connect Chatling once
Add your Chatling connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.