iflow-mcp_mobvoi-mcp 0.1.0

Official Mobvoi Model Context Protocol (MCP) server that enables interaction with Mobvoi powerful Text to Speech, Voice Clone, Photo-Driven Avatar, Video Dubbing, Video Translation APIs. This server allows MCP clients like Cursor, Claude Desktop, Cline , Windsurf and other Client to call tools to generate speech, clone voices, photo drive avatar, video dubbing, video translation and more. The mobvoi-mcp server is built based on Python, our PyPI package is published at Pypi, you can click on Pypi to view the latest version.

Prerequisite

1. python 3.10+;
2. Get your app_key and app_secret:
   • For users in mainland China: you can get your APP_KEY and APP_SECRET from Mobvoi Sequence Monkey open platform. New users can claim a free quota.
   • For overseas users: we will launch it soon.
3. Configure environment variables such as APP_KEY, APP_SECRET, MOBVOI_MCP_REGION, and MOBVOI_MCP_BASE_PATH. I will provide example explanations later.
   • MOBVOI_MCP_REGION："mainland" by default. Overseas users need to configure "global"(coming soon).
   • MOBVOI_MCP_BASE_PATH：The storage path for tool invocation results.
4. Install uv (Python package manager), install with pip install uv or see the uv repo for additional install methods.

What can Mobvoi MCP do?

Mobvoi MCP now provides the following tools for Clients to invoke.

Quickstart with Cursor

Go to Cursor -> Cursor Settings -> MCP, click Add new global MCP server, and mcp.json will open, paste the following config content:

"Mobvoi": {
        "command": "uvx",
        "args": [
          "mobvoi-mcp"
        ],
        "env": {
          "APP_KEY": "<insert-your-APP_KEY-here>",
          "APP_SECRET": "<insert-your-APP_SECRET-here>",
          "MOBVOI_MCP_REGION": "optional, mainland is default, choose from mainland | global",
          "MOBVOI_MCP_BASE_PATH": "optional, ~/Desktop is default" 
        },
      },

Quickstart with Claude Desktop

Go to Claude Desktop -> Settings -> Developer, click Edit Config and open claude_desktop_config.json, paste the following config content:

"Mobvoi": {
        "command": "uvx",
        "args": [
          "mobvoi-mcp"
        ],
        "env": {
          "APP_KEY": "<insert-your-APP_KEY-here>",
          "APP_SECRET": "<insert-your-APP_SECRET-here>",
          "MOBVOI_MCP_REGION": "optional, mainland is default, choose from mainland | global",
          "MOBVOI_MCP_BASE_PATH": "optional, ~/Desktop is default"
        },
      },

Quickstart with Cline

Install Cline extension on VSCode EXTENSIONS, and go to Cline -> MCP Servers -> Installed, click Config MCP Servers and cline_mcp_settings.json will be opened, paste the following config content:

"Mobvoi": {
        "command": "uvx",
        "args": [
          "mobvoi-mcp"
        ],
        "env": {
          "APP_KEY": "<insert-your-APP_KEY-here>",
          "APP_SECRET": "<insert-your-APP_SECRET-here>",
          "MOBVOI_MCP_REGION": "optional, mainland is default, choose from mainland | global",
          "MOBVOI_MCP_BASE_PATH": "optional, ~/Desktop is default"
        },
        "transportType": "stdio"
      },

For MacOS and Linux systems, you can refer to the above for configuration. We haven't tested the Windows system yet.

Source Code Test

If you want to conduct tests based on the source code or perform secondary development based on this repository, you can configure it in the following way:

"MobvoiLocal": {
      "disabled": false,
      "timeout": 60,
      "command": "uv",
      "args": [
        "--directory",
        "<path-to-mobvoi-mcp>/mobvoi_mcp",
        "run",
        "server.py"
      ],
      "env": {
          "APP_KEY": "<insert-your-APP_KEY-here>",
          "APP_SECRET": "<insert-your-APP_SECRET-here>",
          "MOBVOI_MCP_REGION": "optional, mainland is default, choose from mainland | global",
          "MOBVOI_MCP_BASE_PATH": "optional, ~/Desktop is default"
      },
      "transportType": "stdio"
    },

Take Cline as an example, and the configuration of other clients is similar.

Example usage

1. TTS Demo video:

Troubleshooting

spawn uvx ENOENT

If you encounter the error "MCP Mobvoi: spawn uvx ENOENT", confirm its absolute path by running this command in your terminal: which uvx Once you obtain the absolute path (e.g., /usr/local/bin/uvx), update your configuration to use that path (e.g., "command": "/usr/local/bin/uvx"). This ensures that the correct executable is referenced.

MCP error -32001: Request timed out

If you encounter this error, this indicates that there is a problem with your network. If you are in mainland China, we strongly recommend that you configure extra pypi sources in the following way:

"Mobvoi": {
        ...
        "args": [
          "--index", 
          "https://pypi.tuna.tsinghua.edu.cn/simple",
          "mobvoi-mcp"
        ],
       ...
      },

Note that the extra pypi source needs to be configured at the very front of the args.

Unable to synchronize the latest PyPI package

If you encounter this situation, it may be caused by the following reasons: 1) Network problems; 2) Cache problems; 3) The specified mirror source has not synchronized the mobvoi-mcp package. If you are using a mirror source, you should first check whether the mobvoi-mcp package is synchronized on the mirror source you are using, in the following way: pip index versions --index-url https://pypi.tuna.tsinghua.edu.cn/simple mobvoi-mcp If you can see that the LATEST version number is consistent with that on PyPI, you can use the mirror source to update the latest mobvoi-mcp package. Otherwise, you can only use https://pypi.org/simple for the update. Usually, after a new package is released on PyPI, there will be a delay of dozens of minutes for the mirror source to synchronize. At the same time, you can refer to the following configuration to update and clear the cache.

"Mobvoi": {
        ...
        "args": [
          "--upgrade",
          "--no-cache-dir",
          "--index", 
          "https://pypi.tuna.tsinghua.edu.cn/simple",
          "mobvoi-mcp"
        ],
       ...
      },