Answer support chats from Cursor

Add Afterchat to Cursor in one click. Cursor's agent reads the chats waiting on you, checks your code and drafts the replies, and every answer is kept for the chat on your site.

The questions that reach a developer are usually about how the product behaves, and Cursor already has the code open. With Afterchat connected over MCP, Cursor's agent can read the conversation, find the answer in the code and write the reply into your support inbox, while the chat on your site keeps answering everything the knowledge vault covers.

Set it up

  1. Add the server. One click opens Cursor with it filled in:

    Add to Cursor

    Or add it by hand to ~/.cursor/mcp.json, under "mcpServers":

    "afterchat": { "url": "https://afterchat.chat/mcp" }
  2. Sign in. Open Cursor Settings, find afterchat in the MCP list and choose Connect. A browser opens on Afterchat. Signing in makes your account if you don't have one, and you pick the workspace and untick anything the agent should not do.

  3. Check it works. In a chat in Agent mode, ask "check Afterchat status". It tells you the workspace, what it may do and what is waiting.

Share it with your team

To give everyone working in the repo the same setup, put the server in the project's own .cursor/mcp.json instead:

{
  "mcpServers": {
    "afterchat": { "url": "https://afterchat.chat/mcp" }
  }
}

Nothing secret goes in the file, since there is no API key. Each person still signs in as themselves, so every agent works as the person who connected it, with that person's role, and your workspace's rules apply to all of them.

What to ask it

No special commands are needed. In Agent mode, ask in plain words:

  • "Check the Afterchat inbox and draft replies to the technical questions."
  • "Look into the conversation about the failing export and check the code."
  • "What is the vault missing? Answer the open questions from the code."
  • "What are customers asking for most?"

Replies wait as drafts in the inbox for your OK, and what the agent learned is kept as an entry that points at the files it read, so the chat on your site can answer that question next time. The tools behind it, and what always waits for a person, are on the MCP server page.

Questions

Does Cursor support remote MCP servers?

Yes. Cursor can add a remote MCP server by its address and sign in to it with OAuth, which is how Afterchat connects. There is no API key to paste.

Can Cursor send replies to customers?

It drafts them. By default a reply waits in the Afterchat inbox until someone approves it, and hold rules keep prices, refunds and legal terms with a person whatever the setting.

Does Afterchat see our code?

No. Cursor reads your code with the access it already has and sends back only the replies, notes and entries it writes.

Does Cursor have to stay open?

No. The chat on your site answers around the clock from the knowledge vault and hands over what it can't answer. Cursor's agent works through those when you ask it to.

What does it cost?

Afterchat is free while in early access, within a monthly AI allowance that covers a small team's chats. Cursor is billed by Cursor as usual.

Works with

MCP server MCP server for customer support Connect Claude Code, Cursor or Codex to your support inbox over MCP. Answer chats from your code, keep every answer, approve what reaches customers. Claude Code Claude Code for customer support Use Claude Code for customer support: one command connects it to your inbox over MCP, it answers from your code, and every answer is kept. Claude Claude for customer support How to use Claude for customer support: add Afterchat from Claude's connector directory, and Claude works your support inbox, drafts replies and keeps your knowledge vault. Codex Customer support in Codex over MCP Connect Codex to your support inbox over MCP with one command. Codex answers support chats from your code, and every answer is kept for the chat on your site.

Read next

Knowledge base An AI support chatbot trained on your docs and your code How to give an AI support chatbot your own knowledge: why crawling your docs is only the start, how short checked entries built from your docs, code and chats answer better, and how to keep them true. Handover When should an AI chatbot hand off to a human? The five moments an AI support chatbot should hand a conversation to a person, what the handover message should say, and how often it happened in a live support chat's first week on its own. Feature requests How to track feature requests from support chats Support chats are where customers say what they wish your product did. How to capture those requests, group different wordings into one, rank them by how many accounts asked, and tell everyone when it ships.