# Run TunnelHQ from your AI assistant

Ask what's down, retest a server or set up your monitoring from the chat you already use, with one sign-in and no key to copy.

[Start Free Trial](https://app.tunnelhq.com/register) [Connect your assistant](https://docs.tunnelhq.com/mcp/)

-   Works with
-   Claude
-   ChatGPT
-   Cursor
-   VS Code

Included on every paid plan.

## Connect once

TunnelHQ hosts the server. You approve each assistant and choose what it can reach.

### Add the server

Paste one address into your assistant. Cursor and VS Code add it with one button.

More: https://docs.tunnelhq.com/mcp/#connect-by-signing-in

### Approve what it reaches

Pick the workspace, all projects or one, and read only or read and write.

More: https://docs.tunnelhq.com/mcp/#approving-the-connection

### Revoke any time

See every connection and when it was last used. Revoking ends it at once.

More: https://docs.tunnelhq.com/mcp/#managing-connections

### Where to paste it

`https://mcp.tunnelhq.com/mcp`

1.  Open **Customize**, then **Connectors**, and choose **Add custom connector**.
2.  Name it TunnelHQ, paste the address and choose **Add**, then **Connect** and sign in.

On a Claude Team plan, an Owner adds it and members choose **Connect**.

1.  Add the server, then type `/mcp`, choose **tunnelhq** and **Authenticate**.

```
claude mcp add --transport http tunnelhq https://mcp.tunnelhq.com/mcp
```

1.  In **Settings**, **Connectors**, **Advanced**, turn on **Developer mode**.
2.  Choose **Create**, paste the address, set **Authentication** to **OAuth**, then sign in.

Developer mode needs a ChatGPT plan that includes it.

1.  Choose **Add to Cursor** under Developers → AI assistants in the dashboard, then **Needs login**.
2.  Or add this to `~/.cursor/mcp.json`:

```
{
  "mcpServers": {
    "tunnelhq": { "url": "https://mcp.tunnelhq.com/mcp" }
  }
}
```

1.  Choose **Add to VS Code** under Developers → AI assistants, then **Trust** and sign in.
2.  Or run **MCP: Add Server**, choose **HTTP** and paste the address.

1.  Add this to the MCP config file from the Cascade panel, save, and sign in when asked:

```
{
  "mcpServers": {
    "tunnelhq": { "serverUrl": "https://mcp.tunnelhq.com/mcp" }
  }
}
```

1.  Use the address with Streamable HTTP and OAuth.

Clients that only take a key can [run the server with an API key](https://docs.tunnelhq.com/mcp/#run-the-server-with-an-api-key).

## Set up by one prompt

Every empty Tunnels and Uptime page has a prompt for your assistant. It finds what you run, asks first, and tests what it adds.

### Copy the prompt

Tunnels, Uptime checks and heartbeats each have one, written for your workspace and project. It's also in each page's Add menu.

More: https://docs.tunnelhq.com/mcp/#prompts-in-the-dashboard

### It asks before adding

It lists what it found, and where, and waits for your OK.

More: https://docs.tunnelhq.com/mcp/#prompts-in-the-dashboard

### Every check tested

It adds each one, runs it once and reports the first results.

More: https://docs.tunnelhq.com/mcp/#prompts-in-the-dashboard

### In your Uptime list

The checks it added, already healthy, next to everything else you watch.

More: https://tunnelhq.com/uptime/

## What it can do

29 tools for tunnels, checks, incidents and subscriptions. None of them deletes.

### Safe by design

It can't delete anything, change billing or API keys, or manage people. Read only can only look.

More: https://docs.tunnelhq.com/mcp/#approving-the-connection

### Read results and history

A tunnel's check history, recent failures and your plan's usage.

More: https://docs.tunnelhq.com/mcp/#tools

### Handle incidents

List incidents with their timelines, acknowledge them and retest the tunnel.

More: https://docs.tunnelhq.com/mcp/#tools

### Add tunnels and checks

Create and edit tunnels, Uptime checks, heartbeats and subscriptions, one or many at once.

More: https://docs.tunnelhq.com/mcp/#tools

### Test before you ship

Test a config, share link or subscription URL, or a batch of them.

More: https://docs.tunnelhq.com/mcp/#tools

### All 29 tools, and what each connection can use

#### Any connection (15)

-   Show who is signed in
-   List workspaces
-   List projects
-   Search monitors
-   List monitors
-   Get a monitor
-   Get a monitor's check history
-   List Uptime checks
-   List recent check results
-   List recent failures
-   List incidents
-   Get an incident
-   List subscriptions
-   Get a subscription
-   Show usage and plan limits

#### Read and write only (14)

-   Add a VPN monitor
-   Update a monitor
-   Update several monitors
-   Run a monitor's test now
-   Run several monitors' tests now
-   Add an Uptime check
-   Update an Uptime check
-   Acknowledge an incident
-   Retest an incident's monitor
-   Add a subscription
-   Update a subscription
-   Sync a subscription now
-   Test a VPN server
-   Test several VPN servers

#### Never

-   Delete monitors, checks or subscriptions
-   See or revoke API keys
-   Change billing or team members

Running a saved tunnel's test, or retesting an incident, uses your workspace's on-demand tests. Want deletes too? [Run the server with an API key](https://docs.tunnelhq.com/mcp/#run-the-server-with-an-api-key).

## Questions

### Which assistants can connect?

Claude, Claude Code, ChatGPT, Cursor, VS Code and Windsurf, or any client that supports MCP over Streamable HTTP with OAuth.

### What should I ask first?

“Which of my tunnels and checks are down right now, and why?” works on a read-only connection. “Show yesterday's incidents and acknowledge the one on the API.” needs Read and write.

### Can it change or delete things?

Only if you allow it. A read-only connection can't change anything. With Read and write it can add, edit, test and acknowledge, but never delete, and it can't reach API keys, billing or team members. Your role still applies: a Viewer's connection can only read.

### Can I keep it to one project?

Yes. Choose one project when you approve it, and it can't see or search the others.

### What does the setup prompt read?

The project you point your assistant at. The Tunnels prompt reads your VPN files, private keys included, so use it with an assistant you trust with those files.

### Does TunnelHQ see my conversation?

No. We receive only the actions your assistant asks for, like listing monitors, and store its tokens only as SHA-256 hashes. [What we store for each connection](https://tunnelhq.com/privacy-policy/#ai-assistants).

### How do I end a connection?

Revoke it under Developers → AI assistants and it ends at once. What it created stays. A connection unused for 90 days ends by itself.

### Which plans include it?

Starter, Pro and Business. [Compare plans](https://tunnelhq.com/pricing/).

Source: https://tunnelhq.com/ai/