Kling AI MCP connector for AI agents

Tools your creative agent reaches for on Kling AI, scoped per user.

CALL ANY TOOL

Generate and track video content end to end, scoped to each user's own Kling AI access.

klingmcp_kling_get_task

Kling get task

Query the status and result of a video generation task.

Parameters

Name

Type

Required

Description

task_id

string

Required

The task ID returned from a generation request.

klingmcp_kling_lip_sync

Kling lip sync

klingmcp_kling_list_models

Kling list models

klingmcp_kling_extend_video

Kling extend video

klingmcp_kling_list_actions

Kling list actions

klingmcp_kling_talking_photo

Kling talking photo

klingmcp_kling_generate_video

Kling generate video

klingmcp_kling_generate_motion

Kling generate motion

klingmcp_kling_get_tasks_batch

Kling get tasks batch

klingmcp_kling_generate_video_from_image

Kling generate video from image

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Kling AI tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["klingmcp"], toolNames: [
    "klingmcp_kling_generate_video",
    "klingmcp_kling_generate_video_from_image",
    "klingmcp_kling_generate_motion"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Generate a 5-second product video from this still image" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["klingmcp"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Generate a 5-second product video from this still image" }],
  tools,
});

// Execute the tool call with the user's vaulted klingmcp credential
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["klingmcp"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Generate a 5-second product video from this still image" }],
  tools,
});

// Tool call runs with the user's vaulted klingmcp credential
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["klingmcp"] }, pageSize: 100,
});

const agent = new Agent({
  name: "klingmcp_agent",
  model: "gemini-2.5-pro",
  instruction: "Kling AI tools scoped to this user",
  tools,
});

await agent.run("Generate a 5-second product video from this still image");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Kling AI MCP tool. Click to copy, paste into your agent, done.

Generate video

Copy the prompt

Copied

Generate a 10-second video of a coffee cup steaming on a table.

Copy the prompt

Copied

Generate a video from this product image, 5 seconds, 9:16.

Copy the prompt

Copied

List the available Kling models for video generation.

Motion and extension

Copy the prompt

Copied

Transfer the dance motion from this reference video onto my character image.

Copy the prompt

Copied

Extend video vid_9a21 by 4 more seconds continuing the same scene.

Copy the prompt

Copied

Generate a video with this image as the start frame and that one as the end frame.

Track generation tasks

Copy the prompt

Copied

Check the status of task_7f2a.

Copy the prompt

Copied

Query the status of these 5 video generation tasks.

Copy the prompt

Copied

List all Kling API actions available to this account.

SEE HOW AUTH WORKS

Your users connect once. Their Kling AI MCP credentials stay vaulted, every call is checked, and every action is logged.

Authorize

Your user connects

Kling AI MCP

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Kling AI MCP

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Kling AI MCP

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Kling AI MCP

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other AI generation connectors.

GTM and RevOps Teams

Competitive intelligence briefing agent

Scans Gong calls for competitor mentions, matches each one to its Notion battlecard, and DMs every affected rep a single Slack digest per cycle. Every call runs as the PMM who owns the briefing, never a shared bot.

GTM and RevOps Teams

Outbound prospecting agent

Searches Apollo for prospects matching your ICP, scores and ranks them, drafts personalized outreach in Gmail, and logs every send to Google Sheets. Mail goes out as the rep, not from a shared inbox.

GTM and RevOps Teams

CRM AI agent

Reads the Granola transcript after every call, extracts next steps and updates the HubSpot record, drafts the follow-up in Gmail, and confirms in Slack, all on the rep's own delegated OAuth.

Support and Ops Teams

Meeting prep

Pulls agenda, participant context, and open action items before every meeting.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Kling AI MCP token looks fine in a demo. In production every generation task looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Kling AI MCP today. Ten connectors tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Kling AI MCP as the user or through a shared key?

As the user. Scalekit resolves the credential of the person who triggered the agent at request time, so every Kling AI MCP action in your audit trail is attributed to a real user, not a shared service account.

Where is the Kling AI MCP token stored?

In an AES-256 encrypted vault with per-tenant namespacing. Tokens are resolved at request time, never enter LLM context, refresh automatically, and can be revoked from one dashboard.

Can I limit what the agent does in Kling AI MCP?

Yes. Filter by tool name in listScopedTools to expose only what you want. Scalekit also enforces scope checks before every API call.

What happens when a user revokes access?

The credential is invalidated at the next tool call. The call fails closed, other users' connections are unaffected, and the revocation is logged in the audit chain.

How does the agent get the finished video without seeing raw credentials?

The agent polls kling_get_task with the task ID returned at generation time. Scalekit resolves the Kling credential server-side on every call; the agent and the LLM never see a raw API key.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit