# Kling AI (China) MCP server

> Create images and videos with Kling AI, manage Elements and query generation tasks from your assistant.

- Listing: https://mcp.tc/i/kling-ai-china
- Connect: use the server's own URL `https://klingai.com/mcp/plugin` (OAuth sign-in at the server); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: OAuth sign-in
- Category: [AI & Machine Learning](https://mcp.tc/c/ai-ml)
- Vendor: Kling AI
- Homepage: <https://klingai.com/>
- Docs: <https://klingai.com/app/mcp/guide>

## About

Connects an assistant to Kling AI's generation service for China-region accounts. It can create images and videos, manage Elements and query the status of generation tasks.

The server is a hosted streamable HTTP endpoint at klingai.com. Users sign in with OAuth, and generation uses Kling credits from the account.

## What it can do

- Create images with Kling models
- Create videos with Kling models
- Manage Elements
- Query generation task status
- Read account credit balance

## Example prompts

- "Generate a short video of a pianist on a ship in big waves."
- "Create an image of a neon-lit street in the rain."
- "Check the status of my latest Kling generation task."
- "How many Kling credits do I have left?"

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport http kling-ai-china https://klingai.com/mcp/plugin
```

2. Start Claude Code, type `/mcp`, pick **kling-ai-china** and choose **Authenticate**. A browser window opens for the Kling AI sign-in.

Add `--scope user` to make it available in every project, not just this one.

### Claude Desktop

1. Open **Customize → Connectors**, click **+ Add**, then **Add custom connector**.

2. Name it **Kling AI (China)** and paste this URL:

```url
https://klingai.com/mcp/plugin
```

3. Click **Add**, then **Connect**, and sign in when Kling AI asks.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

### claude.ai

1. Open the connector form on claude.ai. This button fills in the name and URL for you:

[Add to claude.ai](<https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=Kling%20AI%20%28China%29&connectorUrl=https%3A%2F%2Fklingai.com%2Fmcp%2Fplugin>) (opens connector settings)

2. Check that the URL reads `https://klingai.com/mcp/plugin` and click **Add**.

3. Click **Connect** and sign in when Kling AI asks.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.

### ChatGPT

1. On chatgpt.com, go to **Plugins**, select **+**, then **Add custom MCP server**.

2. Enter a name for the server.

3. Under **Connection**, paste `https://klingai.com/mcp/plugin` as the server URL, then for authentication choose **OAuth**. ChatGPT sends you to Kling AI to sign in.

4. Check **I understand and want to continue**, then select **Create as a plugin**.

Whether you can add a custom MCP server depends on your ChatGPT plan and your workspace permissions (in Business workspaces, admins and owners can).

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=kling-ai-china&config=eyJ1cmwiOiJodHRwczovL2tsaW5nYWkuY29tL21jcC9wbHVnaW4ifQ%3D%3D>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

```json
{
  "mcpServers": {
    "kling-ai-china": {
      "url": "https://klingai.com/mcp/plugin"
    }
  }
}
```

Cursor shows **Needs authentication** next to the server. Click the button beside it to sign in.

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=kling-ai-china&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fklingai.com%2Fmcp%2Fplugin%22%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"kling-ai-china","type":"http","url":"https://klingai.com/mcp/plugin"}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

```json
{
  "servers": {
    "kling-ai-china": {
      "type": "http",
      "url": "https://klingai.com/mcp/plugin"
    }
  }
}
```

VS Code asks you to sign in the first time the server starts.

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

```json
{
  "mcpServers": {
    "kling-ai-china": {
      "serverUrl": "https://klingai.com/mcp/plugin"
    }
  }
}
```

2. Refresh the MCP server list in Cascade and sign in when asked.

Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.

### Codex

```bash
codex mcp add kling-ai-china --url https://klingai.com/mcp/plugin
codex mcp login kling-ai-china
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

```toml
[mcp_servers.kling-ai-china]
url = "https://klingai.com/mcp/plugin"
```

### Gemini CLI

```bash
gemini mcp add --transport http kling-ai-china https://klingai.com/mcp/plugin
```

Then, inside Gemini CLI, run `/mcp auth kling-ai-china` to sign in.

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.

```json
{
  "mcpServers": {
    "kling-ai-china": {
      "type": "http",
      "url": "https://klingai.com/mcp/plugin"
    }
  }
}
```

Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.

Client only starts local servers? Bridge it with `npx -y mcp-remote https://klingai.com/mcp/plugin`.

## Details

- Last checked: 2026-11-18 (reachable, asks for credentials)
- Listed: 2026-11-13
- Updated: 2026-11-13

---
Source: https://mcp.tc/i/kling-ai-china (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report
