SocialDataX 快手 Kuaishou MCP

kuaishou_submit_video_speech_text_by_video_url

提交快手作品视频口播转文字任务；提交后最多等待 240 秒，未完成时返回 job_id 和下一步查询动作。

Input Schema

TableJSON Schema

Name	Required	Description	Default
`video_url`	Yes	快手作品页链接、短链接或分享文案；不要传用户主页链接。如果上一步结果已返回 photo_id，可直接使用 photo_id 入口。

Output Schema

TableJSON Schema

Name	Required	Description
`error`	Yes	失败或过期时的稳定错误结构；非终态或成功时为 null。
`job_id`	Yes	任务 ID。
`status`	Yes	任务状态。
`message`	Yes	面向用户/AI 的状态说明。
`platform`	Yes	任务所属平台。
`source_id`	Yes	任务来源 ID。
`content_id`	Yes	平台内容 ID。
`transcript`	Yes	成功时的口播转文字结果；非终态或失败时为 null。
`is_terminal`	Yes	是否已终态。
`next_action`	Yes	非终态时建议的下一步查询动作。
`content_meta`	Yes	作品上下文信息，便于结合转写内容做口播分析。
`content_type`	Yes	内容类型。
`next_poll_after_seconds`	Yes	建议下次查询前等待的秒数；非终态时可用。

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedJul 17, 2026

changedOutput schema / properties / next_action / anyOf

Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "job_id": {
-        "description": "需要继续查询的 job_id。",
-        "type": "string"
-      },
-      "tool_name": {
-        "description": "下一步建议调用的查询工具。",
-        "type": "string"
-      }
-    },
-    "required": [
-      "tool_name",
-      "job_id"
-    ],
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "arguments": {
+        "additionalProperties": true,
+        "description": "下一步查询工具可直接使用的参数。",
+        "type": "object"
+      },
+      "instruction": {
+        "description": "给 AI/客户端的查询指令，说明如何继续轮询到终态。",
+        "type": "string"
+      },
+      "job_id": {
+        "description": "需要继续查询的 job_id。",
+        "type": "string"
+      },
+      "tool_name": {
+        "description": "下一步建议调用的查询工具。",
+        "type": "string"
+      }
+    },
+    "required": [
+      "tool_name",
+      "job_id",
+      "arguments",
+      "instruction"
+    ],
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]

Changed3 schema fields changedJul 10, 2026

addedOutput schema / properties / content_id

Added value: +{
+  "description": "平台内容 ID。",
+  "type": "string"
+}

addedOutput schema / properties / content_meta

Added value: +{
+  "additionalProperties": false,
+  "description": "作品上下文信息，便于结合转写内容做口播分析。",
+  "properties": {
+    "author": {
+      "anyOf": [
+        {
+          "additionalProperties": false,
+          "properties": {
+            "avatar_url": {
+              "anyOf": [
+                {
+                  "type": "string"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "作者头像链接。"
+            },
+            "name": {
+              "description": "作者昵称。",
+              "type": "string"
+            },
+            "profile_url": {
+              "anyOf": [
+                {
+                  "type": "string"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "作者主页链接。"
+            },
+            "user_id": {
+              "description": "作者用户 ID。",
+              "type": "string"
+            }
+          },
+          "required": [
+            "user_id",
+            "name",
+            "profile_url",
+            "avatar_url"
+          ],
+          "type": "object"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "作者信息。"
+    },
+    "content_url": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "作品链接。"
+    },
+    "description": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "平台作品原始描述、正文或配文。"
+    },
+    "duration_ms": {
+      "anyOf": [
+        {
+          "type": "integer"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "音视频时长，单位毫秒。"
+    },
+    "title": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "作品标题；平台无标题时为 null。"
+    }
+  },
+  "required": [
+    "content_url",
+    "title",
+    "description",
+    "duration_ms",
+    "author"
+  ],
+  "type": "object"
+}

changedOutput schema / required

Previous value: -[
-  "job_id",
-  "status",
-  "is_terminal",
-  "platform",
-  "source_id",
-  "content_type",
-  "transcript",
-  "error",
-  "next_poll_after_seconds",
-  "next_action",
-  "message"
-]New value: +[
+  "job_id",
+  "status",
+  "is_terminal",
+  "platform",
+  "content_id",
+  "source_id",
+  "content_type",
+  "content_meta",
+  "transcript",
+  "error",
+  "next_poll_after_seconds",
+  "next_action",
+  "message"
+]

AddedJun 17, 2026

TDQS

B3.3/5.0

Behavior3/5

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

Annotations already indicate this is not read-only, not idempotent, and not destructive. The description adds specific behavior: it waits up to 240 seconds and returns a job_id if incomplete, along with a next query action. This is valuable context beyond annotations, but it doesn't cover error cases, side effects, or what the job_id represents. Adequate but not rich.

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

Conciseness5/5

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

The description is a single sentence that front-loads the core action, then communicates the async behavior and result handling. Every word earns its place; there is no redundancy or filler. Excellent conciseness and structure.

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

Completeness3/5

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

For an asynchronous submission tool with a follow-up query step, the description mentions the next action but stops short of naming the specific tool (e.g., kuaishou_get_video_speech_text_job). It also omits error scenarios or what triggers failure. Given an output schema exists and the tool is relatively simple, it's partially complete but leaves an agent to guess the exact workflow.

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 100%, and the description of video_url is detailed (types of links, exclusion of profile links, alternative photo_id entry). The tool description itself adds no additional parameter semantics, so it relies entirely on the schema. Baseline 3 is appropriate given the high schema coverage.

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 clearly states the action (submit a video speech-to-text task) and the resource (via video URL). It's direct and unambiguous. However, it doesn't explicitly distinguish itself from the sibling kuaishou_submit_video_speech_text_by_photo_id, so it loses a point for not aiding sibling differentiation.

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?

There is no explicit statement of when to use this tool versus alternatives. It implies the next step (query) but doesn't name kuaishou_get_video_speech_text_job, nor does it contrast with the photo_id version. An agent must infer usage context from the schema description of video_url, which mentions using photo_id if available. This is insufficient guidance.

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

All SocialDataX 快手 Kuaishou MCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?