Skip to main content
Glama
DumplingAI

Dumpling AI MCP Server

Official
by DumplingAI

trim-video

Cut video clips to specific start and end timestamps using a URL. Specify exact time ranges in HH:MM:SS format to extract segments.

Instructions

Trim videos to a specific duration.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
videoUrlYesURL of the video
startTimestampYesStart time in HH:MM:SS
endTimestampYesEnd time in HH:MM:SS

Implementation Reference

  • Handler function that proxies the trim-video request to the external Dumpling AI API endpoint, authenticates with API key, and returns the response as MCP content.
    async ({ videoUrl, startTimestamp, endTimestamp }) => { const apiKey = process.env.DUMPLING_API_KEY; if (!apiKey) throw new Error("DUMPLING_API_KEY not set"); const response = await fetch(`${NWS_API_BASE}/api/v1/trim-video`, { method: "POST", headers: { "Content-Type": "application/json", Authorization: `Bearer ${apiKey}`, }, body: JSON.stringify({ videoUrl, startTimestamp, endTimestamp, requestSource: "mcp", }), }); if (!response.ok) throw new Error(`Failed: ${response.status} ${await response.text()}`); const data = await response.json(); return { content: [{ type: "text", text: JSON.stringify(data, null, 2) }] }; }
  • Zod schema defining the input parameters for the trim-video tool: video URL and start/end timestamps.
    { videoUrl: z.string().url().describe("URL of the video"), startTimestamp: z.string().describe("Start time in HH:MM:SS"), endTimestamp: z.string().describe("End time in HH:MM:SS"), },
  • src/index.ts:622-651 (registration)
    Registration of the 'trim-video' tool using server.tool(), including name, description, input schema, and handler function.
    server.tool( "trim-video", "Trim videos to a specific duration.", { videoUrl: z.string().url().describe("URL of the video"), startTimestamp: z.string().describe("Start time in HH:MM:SS"), endTimestamp: z.string().describe("End time in HH:MM:SS"), }, async ({ videoUrl, startTimestamp, endTimestamp }) => { const apiKey = process.env.DUMPLING_API_KEY; if (!apiKey) throw new Error("DUMPLING_API_KEY not set"); const response = await fetch(`${NWS_API_BASE}/api/v1/trim-video`, { method: "POST", headers: { "Content-Type": "application/json", Authorization: `Bearer ${apiKey}`, }, body: JSON.stringify({ videoUrl, startTimestamp, endTimestamp, requestSource: "mcp", }), }); if (!response.ok) throw new Error(`Failed: ${response.status} ${await response.text()}`); const data = await response.json(); return { content: [{ type: "text", text: JSON.stringify(data, null, 2) }] }; } );

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/DumplingAI/mcp-server-dumplingai'

If you have feedback or need assistance with the MCP directory API, please join our Discord server