cherry-studio/src/main/mcpServers/browser/tools/open.ts
LiuVaayne d41229c69b
Add browser CDP MCP server with session management (#11844)
*  feat: add CDP browser MCP server

* ♻️ refactor: add navigation timeout for browser cdp

* 🐛 fix: reuse window for execute and add debugger logging

*  feat: add show option and multiline execute for browser cdp

*  feat: support multiple sessions for browser cdp

* ♻️ refactor: add LRU and idle cleanup for browser cdp sessions

* Refactor browser-cdp for readability and set Firefox UA

* 🐛 fix: type electron mock for cdp tests

* ♻️ refactor: rename browser_cdp MCP server to browser

Simplify the MCP server name from @cherry/browser-cdp to just browser
for cleaner tool naming in the MCP protocol.

*  feat: add fetch tool to browser MCP server

Add a new `fetch` tool that uses the CDP-controlled browser to fetch URLs
and return content in various formats (html, txt, markdown, json).

Also ignore .conductor folder in biome and eslint configs.

* ♻️ refactor: split browser MCP server into modular folder structure

Reorganize browser.ts (525 lines) into browser/ folder with separate
files for better maintainability. Each tool now has its own file with
schema, definition, and handler.

* ♻️ refactor: use switch statement in browser server request handler

* ♻️ refactor: extract helpers and use handler registry pattern

- Add successResponse/errorResponse helpers in tools/utils.ts
- Add closeWindow helper to consolidate window cleanup logic
- Add ensureDebuggerAttached helper to consolidate debugger setup
- Add toolHandlers map for registry-based handler lookup
- Simplify server.ts to use dynamic handler dispatch

* 🐛 fix: improve browser MCP server robustness

- Add try-catch for JSON.parse in fetch() to handle invalid JSON gracefully
- Add Zod schema validation to reset tool for consistency with other tools
- Fix memory leak in open() by ensuring event listeners cleanup on timeout
- Add JSDoc comments for key methods and classes

* ♻️ refactor: rename browser MCP to @cherry/browser

Follow naming convention of other builtin MCP servers.

* 🌐 i18n: translate pending strings across 8 locales

Translate all "[to be translated]" markers including:
- CDP browser MCP server description (all 8 locales)
- "Extra High" reasoning chain length option (6 locales)
- Git Bash configuration strings (el-gr, ja-jp)
2025-12-16 09:29:30 +08:00

48 lines
1.6 KiB
TypeScript

import * as z from 'zod'
import type { CdpBrowserController } from '../controller'
import { successResponse } from './utils'
export const OpenSchema = z.object({
url: z.url().describe('URL to open in the controlled Electron window'),
timeout: z.number().optional().describe('Timeout in milliseconds for navigation (default: 10000)'),
show: z.boolean().optional().describe('Whether to show the browser window (default: false)'),
sessionId: z
.string()
.optional()
.describe('Session identifier; separate sessions keep separate pages (default: default)')
})
export const openToolDefinition = {
name: 'open',
description: 'Open a URL in a hidden Electron window controlled via Chrome DevTools Protocol',
inputSchema: {
type: 'object',
properties: {
url: {
type: 'string',
description: 'URL to load'
},
timeout: {
type: 'number',
description: 'Navigation timeout in milliseconds (default 10000)'
},
show: {
type: 'boolean',
description: 'Whether to show the browser window (default false)'
},
sessionId: {
type: 'string',
description: 'Session identifier; separate sessions keep separate pages (default: default)'
}
},
required: ['url']
}
}
export async function handleOpen(controller: CdpBrowserController, args: unknown) {
const { url, timeout, show, sessionId } = OpenSchema.parse(args)
const res = await controller.open(url, timeout ?? 10000, show ?? false, sessionId ?? 'default')
return successResponse(JSON.stringify(res))
}