Skip to main content
Glama
DumplingAI

Dumpling AI MCP Server

Official
by DumplingAI

run-js-code

Execute JavaScript code securely in a sandbox environment, with options for NPM commands, JSON parsing, and configurable timeouts. Ideal for testing and automation tasks on the Dumpling AI MCP Server.

Instructions

Execute JavaScript code in a sandbox.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
codeYesJavaScript code
commandsNoNPM install commands
memoryNoMemory allocation in MB
parseJsonNoParse output as JSON
timeoutNoExecution timeout in ms

Implementation Reference

  • The main handler function for the "run-js-code" tool. It retrieves the API key, makes a POST request to the external Dumpling API endpoint for executing JS code in a sandbox, handles errors, and returns the response as MCP content.
    async ({ code, commands, parseJson, timeout, memory }) => { 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/run-js-code`, { method: "POST", headers: { "Content-Type": "application/json", Authorization: `Bearer ${apiKey}`, }, body: JSON.stringify({ code, commands, parseJson, timeout, memory }), }); if (!response.ok) throw new Error(`Failed: ${response.status} ${await response.text()}`); const data = await response.json(); return { content: [{ type: "text", text: JSON.stringify(data, null, 2) }] }; }
  • Zod schema defining the input parameters for the "run-js-code" tool.
    { code: z.string().describe("JavaScript code"), commands: z.string().optional().describe("NPM install commands"), parseJson: z.boolean().optional().describe("Parse output as JSON"), timeout: z.number().optional().describe("Execution timeout in ms"), memory: z.number().optional().describe("Memory allocation in MB"), },
  • src/index.ts:989-1015 (registration)
    Registration of the "run-js-code" tool using server.tool(), specifying name, description, input schema, and handler function.
    server.tool( "run-js-code", "Execute JavaScript code in a sandbox.", { code: z.string().describe("JavaScript code"), commands: z.string().optional().describe("NPM install commands"), parseJson: z.boolean().optional().describe("Parse output as JSON"), timeout: z.number().optional().describe("Execution timeout in ms"), memory: z.number().optional().describe("Memory allocation in MB"), }, async ({ code, commands, parseJson, timeout, memory }) => { const apiKey = process.env.DUMPLING_API_KEY; if (!apiKey) throw new Error("DUMPLING_API_KEY not set"); const response = await fetch(`${NWS_API_BASE}/api/v1/run-js-code`, { method: "POST", headers: { "Content-Type": "application/json", Authorization: `Bearer ${apiKey}`, }, body: JSON.stringify({ code, commands, parseJson, timeout, memory }), }); 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