Skip to main content
Glama
runapi-ai

kling-mcp

by runapi-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

edit_video

Create a Kling task on RunAPI to edit a video using a prompt, source video URL, or task ID. Returns task ID, status, and output URLs.

Instructions

Create a Kling task on RunAPI (edit video). 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.
promptYesVideo description. Declared type: string.
timeout_msNo
aspect_ratioNoOutput aspect ratio; source-only requests require auto. Declared type: string. Known values: "auto", "16:9", "9:16", "1:1".
callback_urlNoWebhook URL for async notifications. Declared type: string.
enable_soundNoEnable synchronized sound generation. Declared type: boolean.
source_task_idNoCompleted compatible task ID; cannot be combined with source_video_url. Declared type: string.
duration_secondsNoOutput duration in seconds. Declared type: integer. Known values: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15.
poll_interval_msNo
source_video_urlNoPublic source video URL; cannot be combined with source_task_id. Declared type: string.
output_resolutionNoOutput resolution. Declared type: string. Known values: "720p", "1080p", "4k".
reference_image_urlsNoOrdered reference image URLs. Declared type: array.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed21 schema fields changedv0.3.0
    • addedInput schema / additionalProperties
      Added value: +{}
    • removedInput schema / properties / aspect_ratio / anyOf
      Removed value: -[
-  {
-    "const": "auto",
-    "type": "string"
-  },
-  {
-    "const": "16:9",
-    "type": "string"
-  },
-  {
-    "const": "9:16",
-    "type": "string"
-  },
-  {
-    "const": "1:1",
-    "type": "string"
-  }
-]
    • changedInput schema / properties / aspect_ratio / description
      Previous value: -"Output aspect ratio; source-only requests require auto."New value: +"Output aspect ratio; source-only requests require auto. Declared type: string. Known values: \"auto\", \"16:9\", \"9:16\", \"1:1\"."
    • addedInput schema / properties / aspect_ratio / type
      Added value: +"string"
    • 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 / duration_seconds / anyOf
      Removed value: -[
-  {
-    "const": 3,
-    "type": "number"
-  },
-  {
-    "const": 4,
-    "type": "number"
-  },
-  {
-    "const": 5,
-    "type": "number"
-  },
-  {
-    "const": 6,
-    "type": "number"
-  },
-  {
-    "const": 7,
-    "type": "number"
-  },
-  {
-    "const": 8,
-    "type": "number"
-  },
-  {
-    "const": 9,
-    "type": "number"
-  },
-  {
-    "const": 10,
-    "type": "number"
-  },
-  {
-    "const": 11,
-    "type": "number"
-  },
-  {
-    "const": 12,
-    "type": "number"
-  },
-  {
-    "const": 13,
-    "type": "number"
-  },
-  {
-    "const": 14,
-    "type": "number"
-  },
-  {
-    "const": 15,
-    "type": "number"
-  }
-]
    • changedInput schema / properties / duration_seconds / description
      Previous value: -"Output duration in seconds."New value: +"Output duration in seconds. Declared type: integer. Known values: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15."
    • addedInput schema / properties / duration_seconds / type
      Added value: +"integer"
    • changedInput schema / properties / enable_sound / description
      Previous value: -"Enable synchronized sound generation."New value: +"Enable synchronized sound generation. Declared type: boolean."
    • removedInput schema / properties / model / enum
      Removed value: -[
-  "kling-v3-omni-edit",
-  "kling-v3-omni-reference"
-]
    • removedInput schema / properties / output_resolution / anyOf
      Removed value: -[
-  {
-    "const": "720p",
-    "type": "string"
-  },
-  {
-    "const": "1080p",
-    "type": "string"
-  },
-  {
-    "const": "4k",
-    "type": "string"
-  }
-]
    • changedInput schema / properties / output_resolution / description
      Previous value: -"Output resolution."New value: +"Output resolution. Declared type: string. Known values: \"720p\", \"1080p\", \"4k\"."
    • addedInput schema / properties / output_resolution / type
      Added value: +"string"
    • changedInput schema / properties / prompt / description
      Previous value: -"Video description."New value: +"Video description. Declared type: string."
    • removedInput schema / properties / prompt / maxLength
      Removed value: -2500
    • removedInput schema / properties / prompt / minLength
      Removed value: -1
    • changedInput schema / properties / reference_image_urls / description
      Previous value: -"Ordered reference image URLs."New value: +"Ordered reference image URLs. Declared type: array."
    • removedInput schema / properties / reference_image_urls / maxItems
      Removed value: -4
    • removedInput schema / properties / reference_image_urls / minItems
      Removed value: -1
    • changedInput schema / properties / source_task_id / description
      Previous value: -"Completed compatible task ID; cannot be combined with source_video_url."New value: +"Completed compatible task ID; cannot be combined with source_video_url. Declared type: string."
    • changedInput schema / properties / source_video_url / description
      Previous value: -"Public source video URL; cannot be combined with source_task_id."New value: +"Public source video URL; cannot be combined with source_task_id. Declared type: string."
  2. Addedv0.2.0

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are present, so the description carries the full behavioral burden. It notes the return values (task id, status, output URLs), but says nothing about asynchronous task creation, polling/wait behavior, authentication, cost, or the mutual exclusivity of source inputs, leaving major behavioral traits undisclosed.

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?

The single sentence is front-loaded with the primary operation and has no filler, and the return-value note is useful. Even though it is terse for a 13-parameter tool, the dimension rewards lack of waste.

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 a complex video-editing task tool with no annotations and no output schema, the description is under-specified. It covers the return shape only briefly and omits the asynchronous workflow, usage context, and source-constraint details that an agent would need beyond the schema.

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

Parameters3/5

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

Schema description coverage is 85%, so the input schema already documents nearly all 13 parameters, including mutual exclusivity notes and known values. The description adds no parameter meaning, so the baseline of 3 applies.

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?

The description states a specific action ('edit video') and the mechanism ('Create a Kling task on RunAPI'), which lets an agent know this is not text-to-video or image-to-video. However it does not explicitly name or differentiate from sibling tools such as extend_video or motion_control, so it falls short of a 5.

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?

The description gives no when-to-use guidance, no alternatives, and no conditions under which this tool should be chosen over sibling video tools. It only labels the operation; the agent must infer usage from the tool name alone.

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