Wixzel Voice

com.wixzel由 wixzel.com 發布官方發布者v0.12.0更新於 Nov 3, 2026

讓 Claude、Cursor 或任何 MCP 客戶端建立語音代理並撥打真實電話。

AI 翻譯由 AI 模型根據下方的原文描述翻譯，可能有誤。

原文描述

Lets Claude, Cursor or any MCP client build voice agents and place real phone calls.

已驗證Streamable HTTP可網頁執行AI 與機器學習

概覽

Wixzel Voice 的託管 MCP 服務（mcp.voice.wixzel.com），由 wixzel.com 發布；需要 OAuth 登入；Streamable HTTP。

暫無 AI 概覽：以下資訊來自註冊中心條目和服務本身。

發布者
wixzel.com
端點
mcp.voice.wixzel.com
文件
docs.voice.wixzel.com
最近檢查

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Wixzel Voice，將其新增到工作區。
  2. 連接 所需的 憑證。它們會被私密儲存，絕不會在公開頁面上展示。
  3. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/com.wixzel%2Fvoice/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。 客戶端會在首次連接時完成 OAuth 登入。

{
  "mcpServers": {
    "wixzel-voice": {
      "type": "http",
      "url": "https://mcp.voice.wixzel.com/mcp"
    }
  }
}

README

wixzel-voice-mcp

[npm] [MIT] Wixzel Voice for AI agents. A Model Context Protocol server that lets Claude Code, claude.ai, Claude Desktop, Cursor, and any other MCP client create voice agents, connect a carrier, place calls, run campaigns, and read what it all cost, using the Wixzel Voice API.

Wixzel Voice: APIs for AI voice agents. One API key, one balance, every voice engine.

One tool per API operation, 56 in all, each annotated so a client knows which are read-only, which delete, and which spend money or make a real phone ring. Three prompts (quickstart, diagnose_call, spend_report) package the common workflows.

Published as wixzel-phone-mcp up to 0.3.0, while the product was briefly called Wixzel Phone. Those releases keep working: api.phone.wixzel.com and mcp.phone.wixzel.com keep serving.

Two ways to run it:

WhereAuth
Hosted, https://mcp.voice.wixzel.com/mcpWixzel's serversOAuth sign-in from the client, or a bearer key
Local, npx -y wixzel-voice-mcpYour machine, stdioWIXZEL_API_KEY in the environment

The console's AI clients page at voice.wixzel.com/connect generates every command below with a key filled in.

Claude Code

bash
# hosted: sign in with your Wixzel account when Claude Code asks (/mcp → Authenticate)claude mcp add --transport http wixzel-voice https://mcp.voice.wixzel.com/mcp
# local: a scoped key from the consoleclaude mcp add wixzel-voice -e WIXZEL_API_KEY=wv_live_... -- npx -y wixzel-voice-mcp

Or commit a .mcp.json so every collaborator gets it:

json
{  "mcpServers": {    "wixzel-voice": {      "command": "npx",      "args": ["-y", "wixzel-voice-mcp"],      "env": { "WIXZEL_API_KEY": "${WIXZEL_API_KEY}" }    }  }}

Then:

/mcp__wixzel-voice__quickstart

claude.ai and Claude Desktop

Settings → Connectors → Add custom connector → https://mcp.voice.wixzel.com/mcp → Connect. You sign in to the console, tick what the client may do, and it receives a scoped key of its own. Disconnect it from the console's AI clients page at any time.

Cursor, Windsurf, VS Code, others

Same shape as .mcp.json above: command npx, args ["-y", "wixzel-voice-mcp"], env WIXZEL_API_KEY. Clients that connect over HTTP but cannot do OAuth send the key as Authorization: Bearer wv_live_....

What the agent can do

FamilyTools
Engineslist_engines
Agentslist_agents get_agent create_agent update_agent delete_agent
Callsplace_call list_calls get_call get_call_transcript hangup_call delete_call
Callerslist_callers get_caller update_caller
Meetingsconnect_meeting_integration get_meeting_integration delete_meeting_integration join_meeting list_meetings get_meeting leave_meeting
SIP trunkslist_sip_trunks get_sip_trunk create_sip_trunk update_sip_trunk delete_sip_trunk check_sip_trunk_status test_sip_trunk get_sip_trunk_logs
Phone numberslist_phone_numbers get_phone_number create_phone_number update_phone_number delete_phone_number
Leadslist_leads get_lead create_lead update_lead delete_lead import_leads
Campaignslist_campaigns get_campaign create_campaign start_campaign pause_campaign delete_campaign
Knowledge baseslist_knowledge_bases get_knowledge_base create_knowledge_base import_knowledge_base import_knowledge_file update_knowledge_base delete_knowledge_base list_knowledge_files add_knowledge_file get_knowledge_file delete_knowledge_file
MCP serverslist_mcp_servers get_mcp_server create_mcp_server update_mcp_server delete_mcp_server refresh_mcp_server connect_mcp_server_oauth
Toolslist_tools get_tool create_tool update_tool delete_tool test_tool
Voiceslist_voices get_voice preview_voice create_voice_clone update_voice delete_voice
Appointmentslist_appointments get_appointment create_appointment update_appointment delete_appointment
Billing & usageget_balance list_ledger_entries create_topup get_usage_summary list_usage_events
API keyslist_api_keys create_api_key rotate_api_key revoke_api_key

Prompts: quickstart (connect a carrier, register a number, build an agent, place a first call), diagnose_call (why did call X fail), spend_report (what did this month cost, and where).

Resources: wixzel://guide (the operating guide the server also sends as its instructions) and wixzel://connection (base URL and whether the key is live or test; never the key itself).

How it keeps the agent honest

  • Money is explicit. place_call, start_campaign, create_topup and create_voice_clone are annotated openWorldHint: true and their descriptions tell the model to confirm with the user first. Clients that gate on annotations will ask before running them.
  • Idempotency is automatic. The two money paths require an Idempotency-Key; the server generates one per call and accepts an explicit idempotency_key for deliberate retries, so a network timeout never turns into two calls.
  • Errors are actionable. Every failure returns the API's machine-readable code, the request_id, and a hint that says what to do: which scope is missing, that the balance is short, that a cursor was mangled.
  • Rate limits are absorbed. A 429 is retried after Retry-After up to twice before the model sees it. Those requests are never charged.
  • Scopes do the gating. The key decides what works. There is no admin scope, and a key cannot create one broader than itself.
  • Secrets stay put. SIP passwords are write-only; API key secrets appear once, in the tool result, and nowhere else. The key this server runs with is never exposed through any tool or resource.

Running the hosted mode yourself

bash
npx wixzel-voice-mcp --http 3939
VariablePurpose
MCP_PORTPort. Default 3939; --http <port> overrides.
MCP_BINDInterface. Default 127.0.0.1; terminate TLS in front rather than binding wider.
MCP_PUBLIC_URLThe URL clients use, e.g. https://mcp.voice.wixzel.com/mcp. Advertised as the OAuth resource.
WIXZEL_API_BASE_URLThe API, which is also the OAuth authorization server. Default https://api.voice.wixzel.com.
WIXZEL_API_VERSIONOptional Wixzel-Version date pin.
WIXZEL_API_KEYStdio mode: the key. HTTP mode: a fallback for requests without a bearer, accepted only when MCP_PUBLIC_URL is a loopback address.

Each request's bearer becomes the API key for a fresh, throwaway MCP server; nothing is shared between requests. A request without a bearer gets a 401 with WWW-Authenticate: Bearer resource_metadata="…", and /.well-known/oauth-protected-resource names the API as the authorization server, which is how connectors discover sign-in on their own. GET /healthz reports liveness.

Development

The source is mirrored at wixzel-voice-sdks; it is developed in the private monorepo that also holds the API, so a change to an endpoint and the change to its tool land together.

bash
npm install                # at the repo rootnpm test -w apps/mcp       # offline: a fake API behind in-memory and HTTP transports, plus a spec-coverage checknpm run build -w apps/mcpnpm run inspect -w apps/mcp   # MCP Inspector against the built server

Tool schemas are hand-written zod. The spec-coverage test compares them against the API's OpenAPI document (docs/openapi.json) in both directions, so an endpoint added to the API fails the build here until it gets a tool.

Not for application code

This server is for AI agents. Application code should use the SDKs: wixzel-voice on npm and wixzel_voice on pub.dev.

License

MIT. Wixzel Voice itself is a hosted service; see voice.wixzel.com for terms.

來源：apps/mcp/README.md，提交 12c0885

工具

0
該伺服器需要登入，因此 SourceWeft 無法在沒有帳號的情況下讀取其工具，也未收錄。已連接帳號所能看到的內容可能因帳號及其權限而異。

版本歷史

1
  1. v0.12.0最新Nov 3, 2026

評分

已滿足適用檢查項的 85%

該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list，或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分