mcpField
V
Voice Analyser Mcp Generate A Tone Of Voice Guide For Your Llm To Follow

Voice Analyser Mcp Generate A Tone Of Voice Guide For Your Llm To Follow

Local
github.com/houtini-aiAI & Agents11Updated 12w ago
Repository

About Voice Analyser Mcp Generate A Tone Of Voice Guide For Your Llm To Follow

Voice Analyser is a retired, experimental project that analyzed published writing to extract a voice profile and generate a Claude Skill. It taught a model through measured examples of sentence rhythm, vocabulary, and argument flow rather than a list of style rules; no further releases are planned.

Key features

  1. 01Analyze published writing samples
  2. 02Measure rhythm and vocabulary
  3. 03Extract argument-flow patterns
  4. 04Generate a Claude Skill

Use cases

  1. 01Creating a writing-voice profile from articles
  2. 02Generating a skill to guide model writing

MCP support

It is described as part of an open-source MCP set, but the README does not specify MCP tools or behavior.

#tone-of-voice#content#content-writing

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "voice-analyser": {
      "command": "npx",
      "args": [
        "-y",
        "@houtini/voice-analyser"
      ]
    }
  }
}
Run commandnpx -y @houtini/voice-analyser

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@houtini/voice-analyser

Tools

3

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
sitemap_urlstringYesURL to XML sitemap (e.g., https://example.com/post-sitemap.xml)
output_namestringYesCorpus identifier/name (e.g., "richard-baxter")
output_dirstringYesDirectory to store corpus files (e.g., "C:/dev/corpus")
max_articlesnumberNoMaximum articles to process (default: 100)
article_patternstringNoOptional regex to filter URLs

Details

From the project README
Houtini

Voice Analyser - retired

This project is no longer maintained.

Voice Analyser extracted a writing voice from published articles and generated a Claude Skill from it - measuring the statistical fingerprint of how someone writes (sentence rhythm, vocabulary, argument flow) and teaching the model by example rather than by rule.

It was always flagged experimental, and it stays interesting, but it is not something we are keeping current. Rather than leave a half-tended tool in the set pretending otherwise, we are retiring it.

What this means for you

  • The npm package still installs. @houtini/voice-analyser is deprecated, not unpublished. Nothing you have running will break.
  • This repository is archived. The code stays readable and every existing link keeps working, but there are no further releases, and issues and pull requests are closed.
  • The skills it generated are yours. They are plain files on your disk and keep working regardless of what happens here.

If you want to carry on with it

The approach is sound and the code is MIT. Fork it. The core idea - measure real samples and teach by example instead of writing a style guide full of rules - holds up well, and it is the same principle behind the voice skills we still use day to day.

The rest of the set

The maintained Houtini MCP servers are listed at github.com/houtini-ai.

Part of the Houtini open-source MCP set. Questions: [email protected].

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.