AI agents and MCP

Updated 15 October 2026

An AI agent such as Claude Code or Cursor can build and run your chatbots for you: create one, add your website to its knowledge, write its instructions, try it, and put it live. It connects to ChatFrom's MCP server: you make an API key in ChatFrom and add one line to your agent.

What it does

ChatFrom has an MCP server, the standard way AI agents use other services. Once your agent is connected, you can ask it in plain words, such as “make a chatbot for lumenlamps.com from its help pages and put it live there”, and it does the steps itself, through the same checks as the dashboard. It works as you: it sees your chatbots and nobody else's, and your plan's limits and credits apply as they do to you.

1. Make an API key

Open Your account and find API keys for AI agents.
Name the key after where it will be used, such as Claude Code on my laptop, and press Make a key.
Copy the key. It starts with cf_ and is shown once: ChatFrom keeps only a fingerprint of it, so nobody can show it to you again. If you lose it, delete it and make a new one.

An account can have 10 keys. One for each agent or computer lets you stop one without stopping the others.

2. Connect your agent

In Claude Code, the simplest way is to copy the line Your account shows with a new key, which has your key in it already, and run it once in your terminal. Written out, with your key in place of cf_your_key, it is:

Claude CodeTerminal

claude mcp add --scope user --transport http chatfrom https://chatfrom.io/api/agent/mcp --header "Authorization: Bearer cf_your_key"

--scope user makes ChatFrom available in every folder you open Claude Code in; without it, only in the folder you ran the command in. To check it, run claude mcp list: ChatFrom should show as connected. A session that was already open does not see it, so start a new one.

In Cursor, add ChatFrom to ~/.cursor/mcp.json, or to .cursor/mcp.json in one project:

CursorJSON

{
  "mcpServers": {
    "chatfrom": {
      "url": "https://chatfrom.io/api/agent/mcp",
      "headers": { "Authorization": "Bearer cf_your_key" }
    }
  }
}

Any other agent that connects to an MCP server over HTTP works the same way: the address is https://chatfrom.io/api/agent/mcp, and the key goes in the Authorization header as Bearer and the key.

What your agent can do

Tools	What they do
`list_chatbots, get_chatbot`	Your chatbots, and one chatbot's instructions, settings, embed snippet and share link.
`create_chatbot`	A new chatbot, as a draft only you can talk to.
`update_chatbot`	Its name, instructions, model, language, welcome message, suggested questions, fallback message, tone and detail.
`find_pages, add_pages`	Finds a website's pages, then adds the ones it picks to the knowledge.
`add_text, add_qa, list_knowledge, remove_source`	Texts and questions with their answers, the list of sources, and removing one.
`ask_chatbot`	Asks the chatbot a question, as you would in Try it, reads its answer and sources, and answers the questions your flows ask.
`deploy_chatbot`	Puts the chatbot live or back to a draft, sets the websites it may run on, and gives the snippet and share link.
`list_conversations, get_conversation`	What visitors asked, filtered to the unanswered, the rated down or the handed off, and one conversation in full.
`get_usage`	The credits used this month, and when they start again.

A good first request is “list my ChatFrom chatbots”: if your agent answers with them, it is connected. Answers from ask_chatbot and adding knowledge use your monthly credits, the same as in the dashboard.

What it cannot do

Delete a chatbot or your account, or change your plan or billing. Those stay in the dashboard, where they ask you to confirm.
Make, see or delete API keys, so a key cannot make another key.
Connect chat apps or services such as WhatsApp or Shopify. You set those up in the dashboard, where they ask for your sign-in or your keys.
Go past your plan: a chatbot, a source or a credit over its limit is refused, with the reason, as it would be for you.

Each key can make 120 requests a minute, more than an agent needs.

Keep your key safe

A key works as you, so treat it like a password: keep it in your agent's settings, never in code you share or a public repository. Someone else with your key could change your chatbots and use your credits.
Your account shows when each key was last used. Delete a key you no longer use, or one you think someone else has seen; it stops working at once.
Deleting your account deletes its keys.

The agent endpoint is described for developers in the API reference. To set up a chatbot yourself, step by step, see Getting started.