An MCP server for customer support

Connect Claude Code, Cursor, Codex or any MCP client to your support inbox. Your agent reads the chats, checks your code and writes the replies, and every answer is saved so the chat on your site handles it next time.

The Northwind demo workspace: a question the chat hands over, Claude Code answering it from the code, the reply waiting for approval, and the answer saved for next time.

What an MCP server for customer support does

The Model Context Protocol (MCP) is an open standard for connecting AI agents to outside tools. A support tool that runs an MCP server lists what an agent may do there, like reading a conversation or drafting a reply, and the agent calls those tools itself instead of you copying chats into a prompt.

Afterchat is a support chat built to be worked this way. The chat on your site answers what your knowledge vault covers and hands the rest to your team. Your coding agent picks up what was handed over, reads the code it needs and writes the reply. What it learned goes back into the vault, so the chat on your site can answer that question itself the next time someone asks.

Connect your agent

The server is at https://afterchat.chat/mcp. It signs in with OAuth in your browser, so there is no API key to paste.

Claude Code

claude mcp add --transport http --scope user afterchat https://afterchat.chat/mcp

Restart Claude Code, run /mcp, pick afterchat and choose Authenticate. Claude Code in detail

Claude

In Claude on the web or the desktop app, add Afterchat from Claude's connector directory, then Connect. Claude in detail

Cursor

Add to Cursor

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

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

Then open Cursor Settings, find afterchat in the MCP list and choose Connect. Cursor in detail

Codex

codex mcp add afterchat --url https://afterchat.chat/mcp

Then sign in with codex mcp login afterchat. Codex in detail

VS Code

Add to VS Code

code --add-mcp '{"name":"afterchat","type":"http","url":"https://afterchat.chat/mcp"}'

Then start the afterchat server from the MCP list and allow the sign-in.

Any other MCP client

Add a remote HTTP server named afterchat with the address above. Or paste this line into the agent and let it set itself up:

Connect Afterchat to this agent: fetch https://afterchat.chat/agent-setup.md and follow it.

When the browser opens, signing in makes your account if you don't have one yet. You pick the workspace and untick anything your agent should not do. Then ask the agent to "check Afterchat status", and it tells you the workspace, what it may do and what is waiting.

What your agent can do

The server has 22 tools in three groups, one for each thing a support chat leaves behind.

GroupToolsWhat it is for
Inboxlist and read conversations, reply, add a team note, closeAnswering what was handed over, with the code open
Vaultsearch, list entries and gaps, write an entry or a guide, check what a code change affects, organize topics, merge or archive, act on tidy-up suggestionsKeeping what the chat answers from correct and complete
Requestslist requests, get a request's brief, ask the people who requested it, shipBuilding what customers asked for, then telling them it is done

Eight prompts package the common jobs. In Claude Code they show up as slash commands, like /mcp__afterchat__inbox.

PromptWhat it does
inboxWorks through the conversations waiting on you, technical ones first
investigateDigs into one conversation with the code and your own tools
gapsAnswers the questions the vault is missing, from the code
vaultBuilds or improves the vault: topics, entries, merges and guides
reviewChecks unchecked answers and tidy-up suggestions against the code
triageLays out the ranked requests, for deciding what to build
buildLoads a request's brief to build from
shipTells everyone who asked and updates the vault, once you approve

What waits for you

  • Replies to customers wait as drafts in the inbox until someone on your team approves them, unless an owner lets them go out at once.
  • Hold rules keep some things with a person whatever else is set: prices and amounts, limits and quotas, refunds and cancellations, terms and legal, code and file paths in replies, and changes to entries your team checked. You can add words of your own.
  • Public changes to your help content, and shipping a request, which emails everyone who asked for it, wait on the Coding agent page for a yes.
  • You choose what it may do when you connect it. Every connected agent is listed in Afterchat, where it can be disconnected.
  • Everything it does is logged with the connection that did it, and a change can be undone.
  • Customer messages are data, never instructions. A customer writing "ignore your instructions" is text in a quote, and nothing Afterchat sends tells your agent to run something.

Your code stays with you

Afterchat never holds your code, your credentials or a connection to your systems. Your agent reads the code with the access you already gave it, and sends back only what it writes: a reply, a note on the conversation, an entry for the vault. An entry written from the code keeps the paths of the files it came from, so after a change your agent can check which answers the change made wrong.

The chat on your site gets none of this access. It answers from the vault only.

How it differs from a help desk's MCP server

Several help desks now publish an MCP server, and some of them only let an agent read. That suits a team that wants an agent to search old tickets. Afterchat was built for the agent to do the work: reply, close a conversation with what it learned, write and merge entries, and build from what customers asked for, all behind the approvals above. Every answer it writes stays in the vault the chat on your site answers from.

Coming from another help desk? You can bring your old chats over in one import, and Afterchat shows what it would have answered before you put the chat on your site.

Questions

What is an MCP server for customer support?

It is a support tool that exposes its inbox, knowledge base and requests through the Model Context Protocol, so an AI agent such as Claude Code, Cursor or Codex can read and act on them with tools, instead of you copying chats into a prompt.

Which agents can connect?

Any MCP client that can add a remote HTTP server with OAuth sign-in. Claude Code, Codex, Cursor and VS Code each have a one-line setup on this page, and Claude on the web or the desktop app adds it from Claude's connector directory.

Can the agent send replies on its own?

Only if an owner allows it. By default a reply from an agent waits as a draft in the inbox for a person to approve, and hold rules keep topics like prices and refunds with a person whatever the setting.

Does Afterchat see our code?

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

Does the agent have to run all the time?

No. The chat on your site answers around the clock from the knowledge vault and hands over what it can't answer. Your agent works through what was handed over when you sit down with it.

What does it cost?

Afterchat is free while in early access, within a monthly AI allowance that covers a small team's chats. Your agent's own usage is billed by its provider as usual.

Works with

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. Cursor Customer support in Cursor over MCP Connect Cursor to your support inbox over MCP in one click. Cursor's agent answers support chats from your code, and every answer is kept for the chat on your site. 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

Coding agents How to use Claude Code for customer support How I run customer support from Claude Code over MCP: the setup, what the agent can do, what waits for approval, and 825 real tool calls on FanWake. 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.