Voice and conversation · MCP server
Voicemode: MCP server, setup and security
Voicemode is an open-source MCP server published on GitHub that lets an AI agent hold natural voice conversations using STT and TTS through MCP. Its repository has 1,417 stars and its last commit is from October 21, 2026 and it is licensed under MIT.
| Adoption (stars) | 32/40 | |
|---|---|---|
| Maintenance | 30/30 | |
| Framework (licence, registry, official) | 21/30 |
What Voicemode does
According to its repository: “Natural voice conversations for AI assistants - STT/TTS via MCP”
The Model Context Protocol (MCP) is a standard plug between an AI agent and an outside service: once the server is connected, its tools show up in the agent, which decides when to call them. Voicemode is listed under Voice and conversation, a category of 13 servers in the directory, where it ranks #1 by stars.
Topics declared by the repository: asr, claudecode, kokoro, livekit, tts, voice.
Installing and connecting Voicemode
Distribution modes declared in the official MCP registry:
- PyPI package (Python, started with
uvxorpip)
It works with any MCP-compatible client (Claude Desktop, Claude Code, Cursor, VS Code, Codex and most recent agents). You add one entry to the client's MCP configuration: server name, start command or URL, environment variables. Project language: Python.
The registry lists one secret variable to provide (API key, access token). Keep them in the client's environment variables, never in a shared file or a repository.
Security: what to check
Connecting an MCP server means installing software that talks straight to your agent: it runs with your rights and the model trusts its tool descriptions. The risk therefore depends on what it can touch and how far its code can be trusted.
Points found for Voicemode:
- Secrets: the server acts with your credentials. Create a dedicated key with minimum rights and an expiry date.
Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.
Project activity and maintenance
Created on June 8, 2025, the mbailey/voicemode repository has 1,417 stars and 198 forks, with 32 open issues. It has more stars than 94% of the servers in the directory. It received changes this month. Version published in the registry: 8.12.0 (July 21, 2026).
Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.
Verdict
Voicemode is one of the most solid servers in its category: followed, maintained and well framed.
Strengths
- Active project: recent commit
- Widely followed: 1.4K stars
- Listed in the official MCP registry
- Permissive licence (MIT)
Limitations
- Requires an API key or token
Avoid if…
- You do not want to give credentials to an agent
Alternatives
- AgentPhone124 ★
- PlaceCall105 ★
- Perspective AI6 ★
- Zihin0 ★
- Loudkit26 ★
- Babelscribe6 ★
Learn more
Frequently asked questions
How do I install Voicemode?
Voicemode is distributed as PyPI package (Python, started with uvx or pip). Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of mbailey/voicemode.
Is Voicemode free?
The code is published under the MIT licence and can be used free of charge. It needs an API key: the service it connects to may be paid.
Is Voicemode safe?
Points to watch: secrets. Give it minimum rights and approve sensitive actions.
Is it an official server?
It is published in the MCP registry under the verified namespace dev.voicemode, which shows the publisher controls that domain.
What are the alternatives to Voicemode?
In the same category: AgentPhone, PlaceCall, Perspective AI, and Zihin.
Related articles
- Build your own MCP server in 30 minutesOctober 24, 2026
- Automate your inbox with an AI agentOctober 18, 2026
- MCP, A2A, and tool calling: agent protocols explainedOctober 17, 2026
- Build an AI agent with n8n, without codingOctober 16, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score