Voice Analyser MCP
Stop AI-tells leaking into your long-form. Extract a writer's structural rules from their corpus and hold them while drafting.
In practice.
Analyses writing samples and produces a structured tone-of-voice rule-set the LLM keeps in working memory. The difference between Claude-imitating-the-author and the actual author.
Three steps. Five minutes.
Voice Analyser MCP runs as an MCP server. You install it once, point Claude at it via a small config file, and it's available in every conversation from that point on. The full primer is at how to add an MCP server to Claude Desktop; what follows is the short version.
- 1
Install the package
Open a terminal and run the command below. It installs Voice Analyser MCP globally so Claude can find it from any directory.
npm i -g @houtini/voice-analyser - 2
Add it to your Claude config
In Claude Desktop, open Settings → Developer → Edit Config. Add an entry under
mcpServerspointing at@houtini/voice-analyser. The full primer (with the JSON snippet you can copy) is at how to add an MCP server to Claude Desktop. - 3
Restart Claude
Close Claude Desktop completely and reopen it. The new MCP shows up in the tool list at the bottom of the message box. If it doesn't, the linked primer above has the troubleshooting checklist.
Source, package, docs.
Want it doing something specific to you?
Voice Analyser MCP is free, MIT-licensed, runs as it is. If you want it pointed at your own data, wired to your CRM, or built around a workflow this one doesn't cover, that's a conversation. We build bespoke MCPs for clients. Forty-five minutes, no pitch deck.