Capacitor MCP Server

Capacitor plugin for voice recording

Local serverstdioTypeScript

What is the Capacitor MCP server?

Capacitor plugin for voice recording. The capacitor mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 14 defined tools rather than through you.

What it actually does

The capacitor-voice-recorder plugin allows you to record audio on Android, iOS, and Web platforms. Below is a summary of the key methods and how to use them.

Its toolset

Everything the assistant can do here goes through one of these:

  • Maintainer — GitHub
  • canDeviceVoiceRecord — ✅
  • requestAudioRecordingPermission — ✅
  • hasAudioRecordingPermission — ✅
  • startRecording — ✅
  • stopRecording — ✅
  • pauseRecording — ✅
  • resumeRecording — ✅
  • getCurrentStatus — ✅
  • COULD_NOT_QUERY_PERMISSION_STATUS — Failed to query permission status
  • directory — Specifies a Capacitor Filesystem Directory
  • subDirectory — Specifies a custom sub-directory (optional)

Adding it to your client

Installation goes through your MCP client rather than a global install: point it at cap on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

When to reach for it

Plenty of file and storage access servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Capacitor's toolset — Maintainer, canDeviceVoiceRecord, requestAudioRecordingPermission and 11 more — is a fair guide to whether it matches your workflow. It is maintained by tchvu3; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Capacitor.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the capacitor mcp server does with a few real requests.

Available tools

ToolWhat it does
MaintainerGitHub
canDeviceVoiceRecord
requestAudioRecordingPermission
hasAudioRecordingPermission
startRecording
stopRecording
pauseRecording
resumeRecording
getCurrentStatus
COULD_NOT_QUERY_PERMISSION_STATUSFailed to query permission status.
directorySpecifies a Capacitor Filesystem [Directory](https://capacitorjs.com/docs/apis/filesystem#directory)
subDirectorySpecifies a custom sub-directory (optional)
MISSING_PERMISSIONRequired permission is missing.
DEVICE_CANNOT_VOICE_RECORDDevice/browser cannot record audio.

How to install the Capacitor MCP server

{
  "mcpServers": {
    "voice-recorder": {
      "command": "npx",
      "args": ["-y", "cap"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Capacitor to Maintainer.
  • Use Capacitor to canDeviceVoiceRecord.
  • Use Capacitor to requestAudioRecordingPermission.

Frequently asked questions

It connects Capacitor to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (Maintainer, canDeviceVoiceRecord, requestAudioRecordingPermission, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Capacitor directly.