Chatfrom

npx add-mcp 'https://chatfrom.io/api/agent/mcp'

AI agents and MCP

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 orbitdesk.io 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

1. Open Account in the sidebar and find API keys for AI agents.
2. Name the key after where it will be used, such as Claude Code on my laptop, and press Make a key.
3. 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 the Account page 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.

Connect from Claude, without a key

Claude's connectors sign you in instead of asking for a key. Open ChatFrom in Claude's directory, add it and press Connect. ChatFrom asks you to sign in and shows what Claude will be able to do; press Allow and you are back in Claude. A custom connector with the address https://chatfrom.io/api/agent/mcp does the same.

You can see and disconnect the apps you connected this way under Account, in Connected apps. Disconnecting one stops it at once. An app connected like this can do what the agent endpoint lets a key do, and what it cannot do is the same too.

If an agent you gave a key to asks you to sign in instead, the key no longer works. Make a new one under Account.

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; its guardrails; memory; and whether it hands a conversation to a person, and to your own email or one you already confirmed.
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, whether it runs in mobile apps, and how the widget looks, 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.
list_evaluations, add_evaluation_dataset, run_evaluation	Test questions with what a good answer does, and a scored run against them, billed to your OpenRouter key.
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.
• Send hand-offs to a new email address. It can set the address you sign in with, or one already confirmed for another of your chatbots; any other you set under Behaviour, which sends that address a link to confirm.
• 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.
• The Account page 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.
• Conversations hold what your visitors wrote. When your agent reads them, their words go to your agent and to the company whose AI model it runs on, and a visitor can write words meant to steer it. ChatFrom's tools tell your agent to read them as information, never as instructions; read what it proposes before it acts on a conversation.

The agent endpoint is described for developers in the API reference. The same keys work for the n8n node and the browser extension. To set up a chatbot yourself, step by step, see Getting started.