KlingMCP

A Model Context Protocol (MCP) server for AI video generation using Kling through the AceDataCloud API.

Generate AI videos, extend clips, and transfer motion directly from Claude, VS Code, or any MCP-compatible client.

Features

• Text to Video - Create AI-generated videos from text prompts
• Image to Video - Generate videos using reference start/end images
• Video Extension - Extend existing videos with additional content
• Motion Transfer - Transfer motion from a reference video to a character image
• Multiple Models - Support for 9 Kling models, including V3, V3 Omni, and canonical Kling O1
• Camera Control - Fine-grained camera movement control
• Task Tracking - Monitor generation progress and retrieve results

Tool Reference

Quick Start

1. Get Your API Token

1. Sign up at AceDataCloud Platform
2. Go to the API documentation page
3. Click "Acquire" to get your API token
4. Copy the token for use below

2. Use the Hosted Server (Recommended)

AceDataCloud hosts a managed MCP server — no local installation required.

Endpoint: https://kling.mcp.acedata.cloud/mcp

All requests require a Bearer token. Use the API token from Step 1.

Claude.ai

Connect directly on Claude.ai with OAuth — no API token needed:

1. Go to Claude.ai Settings → Integrations → Add More
2. Enter the server URL: https://kling.mcp.acedata.cloud/mcp
3. Complete the OAuth login flow
4. Start using the tools in your conversation

Claude Desktop

Add to your config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "kling": {
      "type": "streamable-http",
      "url": "https://kling.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Cursor / Windsurf

Add to your MCP config (.cursor/mcp.json or .windsurf/mcp.json):

{
  "mcpServers": {
    "kling": {
      "type": "streamable-http",
      "url": "https://kling.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

VS Code (Copilot)

Run MCP: Open User Configuration from the command palette and merge this entry into servers, preserving existing settings. This applies to the current VS Code Profile. Replace YOUR_API_TOKEN locally; keep this token-bearing file private and out of version control.

{
  "servers": {
    "kling": {
      "type": "http",
      "url": "https://kling.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Run MCP: List Servers, select and start the server, review the trust prompt, and confirm tools are loaded in Agent mode.

Or install the Ace Data Cloud MCP extension for VS Code, which registers the hosted MCP servers with one-click setup.

JetBrains IDEs

1. Go to Settings → Tools → AI Assistant → Model Context Protocol (MCP)
2. Click Add → HTTP
3. Paste:

{
  "mcpServers": {
    "kling": {
      "url": "https://kling.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Claude Code

Set the API token in the terminal that will launch Claude Code:

export ACEDATACLOUD_API_TOKEN='YOUR_API_TOKEN'
claude mcp add kling --scope user --transport http https://kling.mcp.acedata.cloud/mcp \
  --header 'Authorization: Bearer ${ACEDATACLOUD_API_TOKEN}'

For a project instead, merge this entry into the root .mcp.json, preserving existing settings:

{
  "mcpServers": {
    "kling": {
      "type": "http",
      "url": "https://kling.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer ${ACEDATACLOUD_API_TOKEN}"
      }
    }
  }
}

On Windows PowerShell, set $env:ACEDATACLOUD_API_TOKEN = 'YOUR_API_TOKEN' instead of export. Start claude from that same terminal; new terminals and desktop launches must also have access to the variable. Run /mcp in the session to confirm connection and loaded tools, and review the approval prompt for project servers. Never commit a real token.

Cline

Open MCP Servers → Configure → Configure MCP Servers in Cline, or edit ~/.cline/mcp.json for Cline CLI. Merge this entry into mcpServers, preserving existing settings. Replace YOUR_API_TOKEN locally; this user configuration contains the token, so do not commit or share it.

{
  "mcpServers": {
    "kling": {
      "type": "streamableHttp",
      "url": "https://kling.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Keep autoApprove empty, confirm the server is connected and tools are loaded, and review permissions on the first tool call.

Amazon Q Developer

Add to your MCP configuration:

{
  "mcpServers": {
    "kling": {
      "type": "streamable-http",
      "url": "https://kling.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Roo Code

Add to Roo Code MCP settings:

{
  "mcpServers": {
    "kling": {
      "type": "streamable-http",
      "url": "https://kling.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Continue.dev

Add to .continue/config.yaml:

mcpServers:
  - name: kling
    type: streamable-http
    url: https://kling.mcp.acedata.cloud/mcp
    headers:
      Authorization: "Bearer YOUR_API_TOKEN"

Zed

Add to Zed's settings (~/.config/zed/settings.json):

{
  "language_models": {
    "mcp_servers": {
      "kling": {
        "url": "https://kling.mcp.acedata.cloud/mcp",
        "headers": {
          "Authorization": "Bearer YOUR_API_TOKEN"
        }
      }
    }
  }
}

cURL Test

# Health check (no auth required)
curl https://kling.mcp.acedata.cloud/health

# MCP initialize
curl -X POST https://kling.mcp.acedata.cloud/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}}}'

3. Or Run Locally (Alternative)

If you prefer to run the server on your own machine:

# Install from PyPI
pip install mcp-kling
# or
uvx mcp-kling

# Set your API token
export ACEDATACLOUD_API_TOKEN="your_token_here"

# Run (stdio mode for Claude Desktop / local clients)
mcp-kling

# Run (HTTP mode for remote access)
mcp-kling --transport http --port 8000

Claude Desktop (Local)

{
  "mcpServers": {
    "kling": {
      "command": "uvx",
      "args": ["mcp-kling"],
      "env": {
        "ACEDATACLOUD_API_TOKEN": "your_token_here"
      }
    }
  }
}

Docker (Self-Hosting)

docker pull ghcr.io/acedatacloud/mcp-kling:latest
docker run -p 8000:8000 ghcr.io/acedatacloud/mcp-kling:latest

Clients connect with their own Bearer token — the server extracts the token from each request's Authorization header.

Available Models

Configuration

Environment Variables

Command Line Options

mcp-kling --help

Options:
  --version          Show version
  --transport        Transport mode: stdio (default) or http
  --port             Port for HTTP transport (default: 8000)

Development

Setup Development Environment

# Clone repository
git clone https://github.com/AceDataCloud/KlingMCP.git
cd KlingMCP

# Create virtual environment
python -m venv .venv
source .venv/bin/activate  # or `.venv\Scripts\activate` on Windows

# Install with dev dependencies
pip install -e ".[dev,test]"

Run Tests

# Run unit tests
pytest

# Run with coverage
pytest --cov=core --cov=tools

# Run integration tests (requires API token)
pytest tests/test_integration.py -m integration

Code Quality

# Format code
ruff format .

# Lint code
ruff check .

# Type check
mypy core tools

Build & Publish

# Install build dependencies
pip install -e ".[release]"

# Build package
python -m build

# Upload to PyPI
twine upload dist/*

Project Structure

KlingMCP/
├── core/                   # Core modules
│   ├── __init__.py
│   ├── client.py          # HTTP client for Kling API
│   ├── config.py          # Configuration management
│   ├── exceptions.py      # Custom exceptions
│   ├── oauth.py           # OAuth 2.1 provider
│   ├── server.py          # MCP server initialization
│   ├── types.py           # Type definitions
│   └── utils.py           # Utility functions
├── tools/                  # MCP tool definitions
│   ├── __init__.py
│   ├── video_tools.py     # Video generation tools
│   ├── motion_tools.py    # Motion transfer tools
│   ├── task_tools.py      # Task query tools
│   └── info_tools.py      # Information tools
├── prompts/                # MCP prompts
│   └── __init__.py        # Prompt templates
├── tests/                  # Test suite
│   ├── conftest.py
│   └── __init__.py
├── deploy/                 # Deployment configs
│   └── production/
│       ├── deployment.yaml
│       ├── ingress.yaml
│       └── service.yaml
├── .env.example           # Environment template
├── CHANGELOG.md
├── Dockerfile             # Docker image for HTTP mode
├── docker-compose.yaml    # Docker Compose config
├── LICENSE
├── main.py                # Entry point
├── pyproject.toml         # Project configuration
└── README.md

API Reference

This server wraps the AceDataCloud Kling API:

• Kling Videos API - Video generation (text2video, image2video, extend)
• Kling Motion API - Motion transfer
• Kling Tasks API - Task queries

Contributing

Contributions are welcome! Please:

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing)
5. Open a Pull Request

Documentation

Documentation

License

MIT License - see LICENSE for details.

Links

• AceDataCloud Platform
• Kling AI
• Model Context Protocol
• MCP Python SDK

Made with love by AceDataCloud

Turbo, storyboards and commerce

Use kling_generate_turbo_video for V3 Turbo (std 720p / pro 1080p, integer 3–15 seconds). Native audio is included and cannot be disabled. Tail frames, standalone negative prompts, cfg_scale, camera controls and Omni references are unsupported.

Use kling_generate_storyboard for V3/V3 Omni multishot generation: shot_type="intelligence" uses a prompt; customize takes 1–6 indexed multi_prompt shots whose durations sum to the total. For example: {"shot_type":"customize","duration":5,"multi_prompt":[{"index":1,"prompt":"Ocean","duration":2},{"index":2,"prompt":"Beach","duration":3}]}.

Public commerce tools are kling_goods_studio and kling_video_commerce. Both accept a structured request and return a task ID for kling_get_task.

Reference inputs

Use element_list and voice_list only with already valid platform references and the supported model combinations in the current backend guide. Standalone asset creation and management are not published.