kling-mcp
This server provides MCP-compatible access to Kling video generation on RunAPI, including authentication, pricing lookup, task creation, and status polling.
Authenticate with RunAPI via browser PKCE login (
login) orRUNAPI_API_KEY.Check Kling pricing by model and endpoint without auth (
check_pricing).Create Kling tasks for: AI avatar, video editing, video extension, image-to-video, motion control, and text-to-video.
Submit tasks asynchronously (
wait: false) or poll until a terminal status.Fetch current status and output payloads for existing tasks (
get_task).Use 16 Kling model variants across 6 endpoints with model-specific parameters like prompts, image/video URLs, duration, resolution, sound, and webhooks.
Note: retired models
kling-ai-avatar-v1-proandkling-v1-avatar-standardreturn HTTP 410 for new requests; existing tasks remain queryable.
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., "@kling-mcp Create a text-to-video task with kling-3.0"
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.
Why This Package?
@runapi.ai/kling-mcp is a focused Model Context Protocol server for the Kling model line on RunAPI.
It gives MCP-compatible assistants direct access to 6 endpoints and 16 model variants without loading the full RunAPI catalog.
Use this per-model server when an agent should stay scoped to Kling. Use @runapi.ai/mcp when one assistant should discover every RunAPI model line.
kling-ai-avatar-v1-pro was retired on 2026-10-14T00:00:00Z. New requests return HTTP 410 before task creation or balance deduction. Existing tasks can still be queried. This model ID is not mapped to another model.
kling-v1-avatar-standard was retired on 2026-10-14T00:00:00Z. New requests return HTTP 410 before task creation or balance deduction. Existing tasks can still be queried. This model ID is not mapped to another model.
Related MCP server: @runapi.ai/elevenlabs-mcp
Install
Add it to Claude Code:
claude mcp add kling -s user -- npx -y @runapi.ai/kling-mcpUse project scope when the server should be shared with a repository:
claude mcp add kling -s project -- npx -y @runapi.ai/kling-mcpCodex, Cursor, Windsurf, VS Code, Roo Code, and other MCP hosts can use the same stdio command:
{
"mcpServers": {
"kling": {
"command": "npx",
"args": ["-y", "@runapi.ai/kling-mcp"]
}
}
}check_pricing works before sign-in. For task creation and status polling, ask your assistant to call the login tool. It opens a browser login and saves credentials to ~/.config/runapi/config.json, the same file used by runapi login.
Headless and CI hosts can still set RUNAPI_API_KEY before starting the MCP host.
Ready-made examples are in examples/ for Claude, Cursor, Windsurf, VS Code, and Roo Code.
Tools
Tool | Auth | Purpose |
| Yes | Create a Kling ai avatar task and optionally wait for a terminal status. Returns the task id, status, and output URLs. |
| Yes | Create a Kling edit video task and optionally wait for a terminal status. Returns the task id, status, and output URLs. |
| Yes | Create a Kling extend video task and optionally wait for a terminal status. Returns the task id, status, and output URLs. |
| Yes | Create a Kling image to video task and optionally wait for a terminal status. Returns the task id, status, and output URLs. |
| Yes | Create a Kling motion control task and optionally wait for a terminal status. Returns the task id, status, and output URLs. |
| Yes | Create a Kling text to video task and optionally wait for a terminal status. Returns the task id, status, and output URLs. |
| Yes | Fetch the current status and latest payload for an existing task. |
| No | Look up current pricing for a Kling model and endpoint. |
Models
Kling covers 16 model variants across 6 endpoints. Each tool accepts the models listed for it:
Tool | Models |
|
|
|
|
|
|
|
|
|
|
|
|
Model availability can change between releases. Use check_pricing or the Kling model page for the current catalog view.
Agent Prompts
Ask your assistant in natural language; it can inspect pricing, create the task, and return the task id plus output URLs.
Create a task
Run a Kling ai avatar task with RunAPI.The assistant can call check_pricing, then ai_avatar, and return the task id, status, and output URLs.
Submit without waiting
Create the task but don't wait for it to finish.The assistant calls the create tool with wait: false and returns the task id. Check on it later with get_task.
Check pricing before creating
Check current Kling pricing, then create the task if it matches my request.The assistant calls check_pricing and can link to the Kling model page for the canonical catalog entry.
Configuration
The server resolves auth in this order:
RUNAPI_API_KEYenvironment variable, useful for headless and CI hosts~/.config/runapi/config.json, created by the MCPlogintool orrunapi loginNo key, which still allows
check_pricing
The config file is normally managed by login. A pre-provisioned headless config can use:
{
"apiKey": "your_runapi_key"
}Do not commit real API keys.
Links
Resource | URL |
Kling model page | |
npm package | |
GitHub repository | |
RunAPI MCP overview | |
RunAPI docs |
License
Licensed under the Apache License, Version 2.0.
Available Tools
9 toolsai_avatarC
Create a Kling task on RunAPI (ai avatar). Returns a task id, status, and output URLs.
Inputs: prompt (required), source_audio_url (required), source_image_url (required), wait, +4 more.
check_pricingC
Look up RunAPI pricing for the kling model line.
Inputs: model, action.
edit_videoC
Create a Kling task on RunAPI (edit video). Returns a task id, status, and output URLs.
Inputs: prompt (required), wait, model, timeout_ms, +9 more.
extend_videoC
Create a Kling task on RunAPI (extend video). Returns a task id, status, and output URLs.
Inputs: source_task_id (required), mode, wait, model, +4 more.
get_taskB
Fetch the current status and latest result payload for a kling task.
Inputs: action (required), task_id (required).
image_to_videoB
Create a Kling task on RunAPI (image to video). Returns a task id, status, and output URLs.
Inputs: prompt (required), first_frame_image_url (required), mode, wait, +15 more.
loginA
Authenticate RunAPI by opening a browser PKCE login flow and saving the API key to ~/.config/runapi/config.json.
Inputs: force.
motion_controlB
Create a Kling task on RunAPI (motion control). Returns a task id, status, and output URLs.
Inputs: source_image_url (required), output_resolution (required), reference_video_url (required), wait, +6 more.
text_to_videoB
Create a Kling task on RunAPI (text to video). Returns a task id, status, and output URLs.
Inputs: mode, wait, model, prompt, +19 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 9 tools
The generation tools (text_to_video, image_to_video, motion_control, ai_avatar, edit_video, extend_video) share near-identical descriptions differing only by the parenthetical task type, but their names clearly signal distinct modalities. login, get_task, and check_pricing are cleanly separate. Only mild overlap between the many generation variants.
Nearly all names use snake_case, and the generation tools follow a consistent verb/resource-to-resource pattern. Slight inconsistency between imperative verbs (login, get_task, check_pricing) and the descriptive generation names, but nothing confusing.
Nine tools is well-scoped for a video-generation API: one auth, one status lookup, one pricing, and six distinct generation modes. Each tool earns its place.
The surface covers auth, all major generation modes, task lookup, and pricing, but lacks task lifecycle management such as listing tasks, canceling, or deleting a task. Agents can poll get_task but cannot enumerate or abort tasks.
Maintenance
Related MCP Connectors
Generate images and videos with Kling AI Global via OAuth. Generation uses account credits.
Generate images and videos (GPT Image, Seedance, Kling, Wan, Qwen) with one API key.
Make images and videos, price requests, list AI models and read your balance, from one API key.
Create and manage cinematic AI video renders through the Future Video Studio Agent API.
Related MCP Servers
AlicenseAqualityFmaintenanceEnables AI video and image generation through the Runway API. Supports video generation from images and text prompts, image creation, video upscaling and editing, and task management.718 npm23MIT- AlicenseBqualityBmaintenanceEnables interaction with ElevenLabs AI models (audio isolation, speech-to-text, text-to-dialogue, sound effects, text-to-speech) through RunAPI, supporting task creation, status polling, and pricing checks.587 npmApache 2.0
- AlicenseBqualityBmaintenanceEnables AI image and video generation tasks (text-to-image, image-to-video, edit, upscale, etc.) via RunAPI, with support for polling and pricing lookups.1084 npm1Apache 2.0
- AlicenseBqualityBmaintenanceEnables creating and polling Luma video modification tasks, fetching task status, and checking pricing via the RunAPI API.358 npmApache 2.0