turn-mcp-web
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@turn-mcp-webAsk for my approval before deploying to production."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
turn-mcp-web
Turn a single agent request into a durable human-in-the-loop conversation.
turn-mcp-web is a self-hosted MCP server with a browser console. An agent calls turn.wait, execution pauses, a human replies in the web UI, and the same run continues without starting over.
Preview
Related MCP server: AskMeMCP
Why It Exists
Most agent integrations treat a human checkpoint as a dead end:
the model asks a question
the run stops
the next message starts a new run with partial context
turn-mcp-web keeps that checkpoint inside the same execution loop.
work -> turn.wait -> human reply -> work -> turn.wait -> human replyThat makes it useful for approvals, branching decisions, operator handoffs, review queues, and long-running assisted workflows.
The tool result is the operator's reply, unchanged. Every wait ends in one terminal state: reply, timeout, cancel, or interrupt. A session that closes, or a server that shuts down, resolves the wait instead of leaving it hanging.
What You Get
MCP tool aliases:
turn.wait,turn_wait,turnbrowser console for live replies
Streamable HTTP transport for IDE MCP clients
stdio entrypoint for desktop clients that spawn MCP servers
REST long-poll API for Python and non-MCP agent frameworks
persistent history and event logging
webhook and Telegram notifications
operator and viewer API roles
session list, quick replies, timeout controls, and live SSE updates
one-command local startup
Quick Start
macOS
Double-click start.command
Windows
Double-click start.bat
Linux
bash start.shFrom Source
npm install
npm run build
npm startWeb console: http://127.0.0.1:3737/
MCP endpoint: http://127.0.0.1:3737/mcp
Core Workflow
Start the server.
Connect your MCP client to
http://127.0.0.1:3737/mcpor launch the stdio entrypoint.Give the agent
skills/turn-mcp-web/SKILL.mdso it routes user-facing checkpoints throughturn.wait.When the agent pauses, answer in the browser console.
The same agent run resumes with your reply.
Client Setup
Streamable HTTP
Use this for Cursor, Windsurf, VS Code, Claude Code, Antigravity, and other MCP clients that support remote HTTP servers.
{
"mcpServers": {
"turn-mcp-web": {
"url": "http://127.0.0.1:3737/mcp"
}
}
}Windsurf uses serverUrl instead of url.
stdio
Use this when the client launches MCP servers as local child processes.
{
"mcpServers": {
"turn-mcp-web": {
"command": "node",
"args": ["/absolute/path/to/dist/server-stdio.js"]
}
}
}The stdio process still opens the same web console on port 3737.
Python
Use the bundled Python client when your framework does not speak MCP directly.
pip install ./python-clientfrom turn_mcp_client import TurnMcpClient, TurnMcpCanceled, TurnMcpTimeout
client = TurnMcpClient("http://127.0.0.1:3737")
try:
reply = client.wait(
context="About to apply a production migration.",
question="Should I proceed?",
options=["Proceed", "Show SQL", "Cancel"],
agent_name="MigrationAgent",
)
print(reply)
except TurnMcpTimeout:
print("No reply before timeout.")
except TurnMcpCanceled:
print("Canceled by operator.")More examples: python-client/README.md
Agent Contract
Give the agent one of these files:
Skill entry:
skills/turn-mcp-web/SKILL.md
Those files tell the agent to use turn.wait as the communication boundary instead of replying directly.
API
Public
GET /healthzGET /api/public-config
Session and wait control
GET /api/waitsGET /api/waits/:idPOST /api/waits/:id/respondPOST /api/waits/:id/cancelPOST /api/waits/:id/extendPOST /api/waits/cancel-allPOST /api/waits/create-and-wait
History and events
GET /api/historyGET /api/history/timelineGET /api/eventsGET /api/stream
Runtime management
GET /api/auth-checkGET /api/sessionsPOST /api/settingsPOST /api/auto-configurePOST /api/auto-unconfigure
Environment
Variable | Default | Purpose |
|
| HTTP bind host |
|
| HTTP bind port |
|
| MCP endpoint path |
|
| Default wait timeout |
| unset | Operator key |
| unset | Viewer key |
| auto | Enable auth |
| unset | JSONL event log path |
| unset | JSONL history path |
| unset | Outbound webhook target |
| unset | Comma-separated webhook events |
| unset | HMAC signing secret |
|
|
|
| unset | Telegram bot token |
| unset | Telegram target chat |
|
| Telegram event filter |
|
| Requests per IP |
|
| Rate limit window |
|
| Per-session concurrency cap |
|
| Process-wide pending wait cap |
|
| Maximum |
|
| Event log entries kept in memory |
Authentication
Auth stays off by default on loopback. Setting an API key turns it on. A non-loopback bind refuses to start unless TURN_MCP_API_KEY is set and auth stays enabled. The browser console is same-origin only: cross-site pages and DNS-rebinding hosts are rejected, and API keys are not accepted in the query string.
When auth is enabled, send either of these headers, or the turn_mcp_key cookie set by the console:
x-turn-mcp-api-key: <key>
Authorization: Bearer <key>Roles:
operator: full controlviewer: read-only inspection and SSE subscription
Docker
docker build -t turn-mcp-web .
docker run --rm -p 3737:3737 \
-e TURN_MCP_HTTP_HOST=0.0.0.0 \
-e TURN_MCP_API_KEY=your_key \
turn-mcp-webCompose file: docker-compose.yml
Repository Layout
src/ TypeScript server
public/ Browser console
python-client/ Python client package
assets/ README screenshots and demo videoContributing
See CONTRIBUTING.md.
License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Give any AI agent a way to ask a person — for approval, a decision, an answer or a review.
Set up human approval for your AI agents' tool calls.
Add human approval to AI agent workflows through cQnce authorization tools.
Checkpoint and resume for AI agent runs, so crashed runs pick up where they left off.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to request human input through a web interface, allowing them to pause execution and wait for responses via interactive tools like single questions, multiple choice selections, hypothesis challenges, and decision workflows.7 npm2MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to request human input through a web interface during execution. Supports single questions, multiple choice selections, hypothesis challenges, and decision workflows for human-in-the-loop interactions.7 npmMIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to pause execution at critical decision points and request human review before proceeding. Provides tools for creating interrupts, polling for decisions, and managing approvals through a simple REST API interface.11 npmMIT
- AlicenseNot gradedqualityBmaintenanceAdds a human-in-the-loop checkpoint to MCP-capable AI coding agents, enabling them to pause and request user feedback before executing actions.12 npm71MIT