Skip to main content
Glama
runapi-ai

kling-mcp

by runapi-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

ai_avatar

Create a Kling task from a face image, audio, and prompt to generate a lip-synced avatar video; returns task ID, status, and output URLs.

Instructions

Create a Kling task on RunAPI (ai avatar). Returns a task id, status, and output URLs.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
waitNoPoll until the task reaches a terminal status.
modelNoRunAPI model slug for this model line.
promptYesDescription of the avatar. Declared type: string.
timeout_msNo
callback_urlNoWebhook URL for async notifications. Declared type: string.
poll_interval_msNo
source_audio_urlYesAudio URL for lip sync. Declared type: string.
source_image_urlYesFace image URL. Declared type: string.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv0.3.0
    • addedInput schema / additionalProperties
      Added value: +{}
    • changedInput schema / properties / callback_url / description
      Previous value: -"Webhook URL for async notifications."New value: +"Webhook URL for async notifications. Declared type: string."
    • removedInput schema / properties / model / enum
      Removed value: -[
-  "kling-ai-avatar-pro",
-  "kling-ai-avatar-standard",
-  "kling-ai-avatar-v1-pro",
-  "kling-v1-avatar-standard"
-]
    • changedInput schema / properties / prompt / description
      Previous value: -"Description of the avatar."New value: +"Description of the avatar. Declared type: string."
    • changedInput schema / properties / source_audio_url / description
      Previous value: -"Audio URL for lip sync."New value: +"Audio URL for lip sync. Declared type: string."
    • changedInput schema / properties / source_image_url / description
      Previous value: -"Face image URL."New value: +"Face image URL. Declared type: string."
  2. Changed3 schema fields changedv0.2.0
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / poll_interval_ms / maximum
      Added value: +9007199254740991
    • addedInput schema / properties / timeout_ms / maximum
      Added value: +9007199254740991
  3. Changed4 schema fields changedv0.1.13
    • addedInput schema / properties / callback_url / description
      Added value: +"Webhook URL for async notifications."
    • addedInput schema / properties / prompt / description
      Added value: +"Description of the avatar."
    • addedInput schema / properties / source_audio_url / description
      Added value: +"Audio URL for lip sync."
    • addedInput schema / properties / source_image_url / description
      Added value: +"Face image URL."
  4. Changed1 schema field changedv0.1.9
    • changedInput schema / required
      Previous value: -[
-  "prompt",
-  "source_audio_url",
-  "source_image_url"
-]New value: +[
+  "source_image_url",
+  "source_audio_url",
+  "prompt"
+]
  5. Changed5 schema fields changedv0.1.2
    • addedInput schema / properties / callback_url / type
      Added value: +"string"
    • addedInput schema / properties / prompt / type
      Added value: +"string"
    • addedInput schema / properties / source_audio_url / type
      Added value: +"string"
    • addedInput schema / properties / source_image_url / type
      Added value: +"string"
    • addedInput schema / required
      Added value: +[
+  "prompt",
+  "source_audio_url",
+  "source_image_url"
+]
  6. First observedv0.1.1

TDQS

C2.9/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden, and it does disclose the return shape (task id, status, output URLs) which is useful given there is no output schema. However, it omits the asynchronous task semantics implied by the wait/poll_interval_ms/timeout_ms parameters, the default blocking poll (wait=true), and any auth or cost considerations despite a sibling check_pricing tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with no filler, and the core purpose is front-loaded before the return-value note. Minor waste in the '(ai avatar)' parenthetical and vendor jargon, but nothing that harms scanning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter generative task tool with no annotations and no output schema, the description covers only the return shape and leaves usage conditions, async/polling behavior, and two parameters entirely unaddressed. An agent has enough to attempt a call but not enough to call it correctly or confidently.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description mentions no parameters at all, and schema coverage is only 75%, below the high-coverage threshold where the schema alone could justify a 3. Two undocumented parameters (timeout_ms, poll_interval_ms) have no meaning supplied anywhere, so the description fails to compensate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Create a Kling task'), and the '(ai avatar)' gloss ties it to the tool name, distinguishing it from sibling video tools like text_to_video and image_to_video. The 'Kling task on RunAPI' phrasing is vendor jargon that only indirectly conveys that this produces a lip-synced avatar from an image plus audio.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance is given: nothing says this is for talking-head/lip-sync avatars requiring an image and audio, nor how it differs from image_to_video or motion_control. The agent must infer applicability purely from the required params.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools