Next Devtools MCP vs Vox
A side-by-side look at the Next Devtools MCP and Vox MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Next Devtools MCP for developer tools work as a local process; choose Vox for text-to-speech. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Next Devtools MCP when
- You need dedicated capabilities in the Developer Tools domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You want tools like
nextjs_index, nextjs_call, nextjs_docs.
Choose Vox when
- You need dedicated capabilities in the Text-to-Speech domain.
- You have the keys it needs:
ELEVENLABS_API_KEY. - You want tools like
listen, speak.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Developer Tools | Text-to-Speech |
| Quality signal | 86/100 · Excellent | 40/100 · Fair |
| Install command | Confirmed | Not confirmed yet |
| Transport | Local subprocess (stdio) | — |
| Auth | No auth required | Not declared |
| Pricing | Free | Not declared |
| Required env vars | None listed | ELEVENLABS_API_KEY |
| Verified owner | Verified | Community listing |
| GitHub stars | 832 | 1 |
| Directory activity | 9 views 0 installs 1 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 4 | 2 |
| Full listing | View Next Devtools MCP | View Vox |
Tools & capabilities
Next Devtools MCP tools 4
nextjs_indexDiscover running Next.js dev servers and list each one's runtime MCP tools.nextjs_callCall a runtime tool on a discovered server (errors, routes, logs, Server Actions).nextjs_docsGateway.** Point the agent at version-accurate docs in `node_modules/next/dist/docs/`.browser_evalGateway.** Point the agent at the [`agent-browser`](https://github.com/vercel-labs/agent-browser) CLI for browser automation.
Vox tools 2
listenActivates the mic, waits for you to speak, returns transcript + detected language when silence is detectedspeakSpeaks text aloud — ElevenLabs TTS with automatic fallback to macOS system voice
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Next Devtools MCP
{
"mcpServers": {
"vercel-next-devtools-mcp": {
"command": "npx",
"args": [
"-y",
"next-devtools-mcp@latest"
]
}
}
}
Vox
No confirmed install command for Vox yet — follow the setup steps linked from its listing page rather than a guessed package name.
Frequently asked questions
Next Devtools MCP is categorized under Developer Tools and uses a local stdio subprocess. Vox belongs to Text-to-Speech and uses an install path we have not confirmed yet. Pick Next Devtools MCP for developer tools work and Vox for text-to-speech.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client. Vox has no confirmed install command yet — follow its own setup instructions.
Next Devtools MCP is listed as free. Auth: no auth required. Vox has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add vercel-next-devtools-mcp and vox as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Next Devtools MCP has a quality signal of 86/100 (Excellent) with 9 views, 0 installs and 832 GitHub stars. Vox has 40/100 (Fair) with 1 views, 0 installs and 1 GitHub stars.