Agent Chat

An MCP server that gives your AI agent a rich chat interface. Markdown, code blocks, canvas diagrams, quick replies, and voice — all in the browser.

See it in swe-swe

Agent Terminal — raw MCP tool calls and code diffs — Agent TerminalThe agent works in the background

Agent Chat — rich rendered conversation with quick replies — Agent ChatA friendly UI to chat with your agent

Rich markdown

Messages render with full markdown, syntax-highlighted code blocks, and blockquotes.

File drag & drop

Drop files into the chat to share them with the agent.

Images in messages

Agents can include screenshots and images inline in their messages.

Canvas drawing

Agents can draw diagrams and visualizations on an interactive canvas.

Voice conversation

Speak to your agent and hear responses via text-to-speech.

Quick replies

Agents can offer clickable response buttons for common actions.

How it works

Agent Chat runs as an MCP server alongside your AI agent. The agent calls tools to communicate with users through a browser-based chat UI.

Agent (Claude, etc.)
  │
  ├─ send_message("Here's what I found...")  →  Chat UI shows rich message
  ├─ draw([...instructions...])              →  Chat UI renders canvas diagram
  ├─ send_progress("Working on it...")       →  Chat UI shows progress indicator
  └─ check_messages()                        ←  Chat UI returns user's reply

MCP Tools

Tool	Description
`send_message`	Send a message and wait for user response. Supports quick reply buttons.
`send_verbal_reply`	Send a spoken reply in voice mode (text-to-speech).
`draw`	Draw a canvas diagram and wait for user response.
`send_progress`	Send a non-blocking progress update.
`send_verbal_progress`	Send a non-blocking spoken progress update.
`check_messages`	Non-blocking check for queued user messages.

Install

Add as an MCP server to Claude Code:

claude mcp add agent-chat -- npx -y @choonkeat/agent-chat