Svara

io.svarapi由 svarapi.io 發布v0.1.0更新於 Oct 24, 2026

Send native LinkedIn voice notes from your AI assistant via the Svara API.

發布方自己的服務：ZenMode

已驗證STDIO僅桌面溝通與協作媒體與設計

服務詳細資訊

識別碼: io.svarapi/mcp
傳輸: STDIO
執行環境: Desktop only
信任: Verified
發布於: Sep 29, 2026

安全提示

MCP 服務會接收對話中的工具呼叫請求，並可能執行外部操作。啟用前請先了解該服務能做什麼，並只授予它所需的權限。

註冊中心已驗證此服務的命名空間屬於 svarapi.io。它以軟體包形式執行，而不是託管端點，因此沒有可與該網域比對的端點。

SourceWeft 的檢查只涵蓋條目是否完整、端點是否回應；不審查伺服器的程式碼，也不審查其工具的行為。

在 README 中新增徽章

向讀者展示該 MCP 服務已收錄於 SourceWeft，徽章連結到本頁。

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.svarapi%2Fmcp.svg)](https://sourceweft.com/mcp/io.svarapi%2Fmcp?utm_source=readme&utm_medium=badge)

概覽

AI 產生的概覽

讓助理透過 Svara API 上傳音訊檔案，並以 LinkedIn 原生語音訊息傳送，支援試跑驗證與傳送狀態查詢。

可以做什麼: 把 Svara REST API 包裝成 MCP 工具：upload_audio 上傳本機音訊檔案（MP3、M4A/AAC、OGG/Opus、WAV 或 WebM，最大 4 MB）並回傳 audio_url；send_linkedin_voice_note 將該音訊以 LinkedIn 原生語音訊息傳給指定收件人（LinkedIn 個人檔案網址或姓名）；get_send_status 回報 queued、sent、failed 或 expired 狀態；get_usage 查看方案用量與額度。傳送預設為試跑，只有把 dry_run 明確設為 false 才會真正送出。
適用情境: 適合讓助理傳送 LinkedIn 語音訊息給你原本就能傳訊的聯絡人，或在正式送出前先做一次驗證。適用於從 Claude、Cursor、VS Code 等 MCP 用戶端發起的聯繫與跟進流程。
執行需求: 需要 Node.js 20 或更新版本以執行 npx svara-mcp；需要 Svara 帳號與 API 金鑰，透過環境變數 SVARA_API_KEY 提供；需要安裝 Svara Chrome 擴充功能，並在該 Chrome 瀏覽器中登入 LinkedIn。僅支援桌面端，且需要連線至 Svara API 的網路。

安裝前請注意

當 dry_run 設為 false 時，send_linkedin_voice_note 會以你自己的 LinkedIn 帳號向真人傳送真實訊息，且無法收回；此工具被標示為破壞性操作，建議保持用戶端確認提示開啟。SVARA_API_KEY 屬於機密，不應外流。傳送受方案額度限制，可能涉及付費方案。

安裝

在 SourceWeft 中

開啟儀表板中的 Svara，將其新增到工作區。
為需要使用其工具的對話啟用該服務。

Desktop only，透過 STDIO。 STDIO 服務會啟動本機處理程序，因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照儲存庫中的啟動說明。

README

Svara MCP server

Send native LinkedIn voice notes from Claude, Cursor, VS Code or any other MCP client.

Svara is a REST API for sending voice notes on LinkedIn. This server exposes it as MCP tools, so your AI assistant can upload a recording, validate a send, deliver a voice note to one of your LinkedIn contacts, and check whether it arrived.

What it does

Upload an audio file (MP3, M4A/AAC, OGG/Opus, WAV or WebM, up to 4 MB).
Send it as a native LinkedIn voice note to someone you can already message on LinkedIn.
Check delivery status (queued, sent, failed, expired).
Check your plan usage.

Sends are dry runs by default: nothing is delivered unless dry_run is explicitly set to false.

Prerequisites

A Svara account and an API key: create one at https://svarapi.io/dashboard.
The Svara Chrome extension installed.
You are signed in to LinkedIn in that Chrome browser.
Node.js 20 or newer (for npx).

Setup

All clients run the same command: npx -y svara-mcp with SVARA_API_KEY in the environment.

Claude Desktop

Add to claude_desktop_config.json (Settings > Developer > Edit Config):

json

{  "mcpServers": {    "svara": {      "command": "npx",      "args": ["-y", "svara-mcp"],      "env": { "SVARA_API_KEY": "your_svara_api_key" }    }  }}

{  "mcpServers": {    "svara": {      "command": "npx",      "args": ["-y", "svara-mcp"],      "env": { "SVARA_API_KEY": "your_svara_api_key" }    }  }}

Claude Code

Cursor

Add to ~/.cursor/mcp.json (or .cursor/mcp.json in a project):

json

{  "mcpServers": {    "svara": {      "command": "npx",      "args": ["-y", "svara-mcp"],      "env": { "SVARA_API_KEY": "your_svara_api_key" }    }  }}

{  "mcpServers": {    "svara": {      "command": "npx",      "args": ["-y", "svara-mcp"],      "env": { "SVARA_API_KEY": "your_svara_api_key" }    }  }}

VS Code

Add to .vscode/mcp.json:

json

{  "inputs": [    { "type": "promptString", "id": "svara-api-key", "description": "Svara API key", "password": true }  ],  "servers": {    "svara": {      "type": "stdio",      "command": "npx",      "args": ["-y", "svara-mcp"],      "env": { "SVARA_API_KEY": "${input:svara-api-key}" }    }  }}

{  "inputs": [    { "type": "promptString", "id": "svara-api-key", "description": "Svara API key", "password": true }  ],  "servers": {    "svara": {      "type": "stdio",      "command": "npx",      "args": ["-y", "svara-mcp"],      "env": { "SVARA_API_KEY": "${input:svara-api-key}" }    }  }}

Tools

Tool	What it does
`upload_audio`	`{ file_path }` Uploads a local audio file and returns an `audio_url`. Sends nothing.
`send_linkedin_voice_note`	`{ recipient, audio_url? , file_path?, dry_run = true }` Sends a voice note. `recipient` is a LinkedIn profile URL (preferred) or name. Give exactly one of `audio_url` or `file_path` (a file is uploaded first).
`get_send_status`	`{ id }` Delivery status of a send.
`get_usage`	`{}` Current plan usage and limits.

Example prompt: "Upload ~/Desktop/intro.m4a and do a dry run of sending it to https://www.linkedin.com/in/example. If it validates, send it for real."

Safety

send_linkedin_voice_note sends a real LinkedIn message to a real person from your own LinkedIn account when dry_run is false. It cannot be unsent.

dry_run defaults to true, which validates the request without sending anything.
The tool is marked as destructive, so MCP clients that support tool annotations will ask you to confirm before it runs. Keep that confirmation on.
Only send to people you can already message on LinkedIn, and only messages you would send yourself.