ext-apps/examples/transcript-server/server.ts
Olivier Chafik 6bb63c3bae
examples: add transcript-server example with live speech transcription (#240)
* feat: add transcript-server example with live speech transcription

- New example: transcript-server with Web Speech API transcription
  - Start/stop recording with timer display
  - Live transcript with interim results
  - Send button to send transcript as ui/message to host
  - Copy button to copy full transcript
  - Sent messages marked with divider, greyed out
  - Experimental ui/update-model-context for live context updates
  - Transparent background, respects host theme

- Enable microphone and clipboard in basic-host sandbox iframes
  - Add allow="microphone; clipboard-write" to both outer and inner iframes
  - Required for Web Speech API, audio capture, and clipboard access

- Add alert popup in basic-host for ui/message from apps

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* style: format transcript-server files

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* test: add e2e test and golden for transcript-server

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* refactor: use @types/dom-speech-recognition instead of hand-rolled types

Removes ~50 lines of manually defined Web Speech API types in favor of
the community-maintained type package.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix: add newlines between transcript chunks when copying to clipboard

* refactor: unify transcript formatting with timestamps

- Add formatEntry() helper that includes [timestamp] prefix
- Add formatEntries() helper that joins entries with newlines
- Use same format for clipboard copy, send message, and model context
- DRY up duplicate code in send button handler

* fix: log model context update failures instead of silently swallowing

* fix: log model context updates for debugging

* refactor: pass permissions through loadSandboxProxy like csp

- Add permissions parameter to loadSandboxProxy in implementation.ts
- Build iframe allow attribute from permissions instead of hardcoding
- Update sandbox.ts to not hardcode allow attribute (set via notification)
- Add microphone + clipboardWrite permissions to transcript-server resource
- Update README to reflect permission configuration via resource _meta.ui

* fix(transcript-server): auto-expand instead of scroll

- Remove min-height: 100vh and overflow-y: auto
- Let content grow naturally with autoResize (default)
- Remove unnecessary scrollTop calls

* test: remove transcript timer mask (no longer dynamic)

* refactor: pass permissions through loadSandboxProxy like csp

* docs: document updateModelContext for transitional speech

* test: update e2e screenshots

* refactor: use app.updateModelContext() instead of raw request

* package-lock.json

* src/generated/schema.json

* test: update e2e screenshots from CI

---------

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-12 21:27:31 +00:00

100 lines
2.6 KiB
TypeScript

import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import type {
CallToolResult,
ReadResourceResult,
} from "@modelcontextprotocol/sdk/types.js";
import fs from "node:fs/promises";
import path from "node:path";
import {
registerAppTool,
registerAppResource,
RESOURCE_MIME_TYPE,
RESOURCE_URI_META_KEY,
} from "@modelcontextprotocol/ext-apps/server";
import { startServer } from "./server-utils.js";
const DIST_DIR = path.join(import.meta.dirname, "dist");
const RESOURCE_URI = "ui://transcript/mcp-app.html";
/**
* Creates a new MCP server instance with tools and resources registered.
*/
export function createServer(): McpServer {
const server = new McpServer({
name: "Transcript Server",
version: "1.0.0",
});
// Register the transcribe tool - opens a UI for live speech transcription
registerAppTool(
server,
"transcribe",
{
title: "Transcribe Speech",
description:
"Opens a live speech transcription interface using the Web Speech API.",
inputSchema: {},
_meta: { [RESOURCE_URI_META_KEY]: RESOURCE_URI },
},
async (): Promise<CallToolResult> => {
return {
content: [
{
type: "text",
text: JSON.stringify({
status: "ready",
message: "Transcription UI opened. Speak into your microphone.",
}),
},
],
};
},
);
// Register the UI resource
registerAppResource(
server,
RESOURCE_URI,
RESOURCE_URI,
{ mimeType: RESOURCE_MIME_TYPE, description: "Transcript UI" },
async (): Promise<ReadResourceResult> => {
const html = await fs.readFile(
path.join(DIST_DIR, "mcp-app.html"),
"utf-8",
);
return {
contents: [
{
uri: RESOURCE_URI,
mimeType: RESOURCE_MIME_TYPE,
text: html,
_meta: {
ui: {
// Request microphone for Web Speech API, clipboard for copy button
permissions: { microphone: {}, clipboardWrite: {} },
},
},
},
],
};
},
);
return server;
}
async function main() {
if (process.argv.includes("--stdio")) {
await createServer().connect(new StdioServerTransport());
} else {
const port = parseInt(process.env.PORT ?? "3109", 10);
await startServer(createServer, { port, name: "Transcript Server" });
}
}
main().catch((e) => {
console.error(e);
process.exit(1);
});