广告合作
MCP.so
登录

Voice Analyser MCP Generate A Tone Of Voice Guide For Your Llm T…

@houtini-ai

代码仓库

基本信息

分类

AI 与智能体

传输方式

stdio

作者

houtini-ai

提交者

Richard Baxter

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

Traditional style guides list rules: "Use short sentences. Vary paragraph length. Include personal anecdotes."

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

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

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "voice-analysis": {
      "command": "npx",
      "args": [
        "-y",
        "@houtini/voice-analyser@latest"
      ]
    }
  }
}

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

3

Crawl sitemap and collect clean writing corpus from published articles

Perform linguistic analysis on collected corpus (vocabulary, sentence structure, voice markers)

Generate v5 EXECUTABLE style guide with example-first format. Zero tolerance rules, phrase libraries, and validation checklists.

概览

What is Voice Analyser Mcp?

Voice Analyser Mcp is an experimental tool that extracts statistical voice models from your published writing and generates immersive style guides for LLMs. It helps replicate your writing voice through pattern recognition and annotated examples, not rules.

How to use Voice Analyser Mcp?

Install via npx and configure in Claude Desktop’s claude_desktop_config.json. Create an output directory, then use the tools collect_corpus, analyze_corpus, and generate_narrative_guide in sequence. After generation, load the voice guide file into any LLM conversation to guide its writing.

Key features of Voice Analyser Mcp

  • Collects articles from an XML sitemap as a corpus
  • Runs 14 analysers on vocabulary, syntax, and voice markers
  • Generates an annotated narrative style guide with examples
  • Detects micro-rhythms like mid-thought pivots and asides
  • Provides statistical targets for sentence length, first-person usage
  • Supports validation of LLM output against the guide’s metrics

Use cases of Voice Analyser Mcp

  • Generate blog posts that match your natural sentence rhythm and conversational devices
  • Write technical articles that follow your argument flow and punctuation habits
  • Produce product reviews that blend personal context with practical detail
  • Draft emails or communications that replicate your hedging/confidence balance
  • Create consistent on-brand content across multiple LLM sessions

常见问题

1

What minimum corpus size does Voice Analyser Mcp require?

Minimum 15,000 words (~20 articles); recommended 30,000; ideal 50,000+. Below 15k words, statistical patterns become unreliable.

2

What are the runtime requirements?

Node.js 20+ is required. The server runs as an MCP tool via npx and is configured in Claude Desktop’s JSON config file.

3

Where does the data live?

All collected articles, analysis JSON files, and the generated voice guide are saved in the output directory you specify. No data is sent to external servers beyond the sitemap crawl.

4

What are the known limitations?

Requires an XML sitemap (RSS not supported). Works best with consistent single-author content. Mixed authorship or heavily edited content produces weaker signals. The approach is experimental.

5

Which transport or auth does Voice Analyser Mcp use?

The server uses standard MCP transport via stdio (command-line). No authentication is needed for local use.

评论

AI 与智能体 分类下的更多 MCP 服务器

BlazingCDN MCP - Content Delivery for Video, Software & Static Files

BlazingCDN

Official MCP server for BlazingCDN - AI agents (Claude, Cursor, Windsurf) manage CDN resources, purge cache, query metrics, domains, Anycast CDN, Video CDN and Media CDN

1

Phi Longevity PRISM

Phi Longevity

Guideline-cited lab-results analysis for people managing type 2 diabetes, kidney disease, lupus and cancer survivorship. Flags tests that are missing or overdue (ADA, KDIGO, NCCN — each cited) and returns questions to br

L

Legion MCP

faulkj

MCP-native LLM councils for debates, juries, blind panels, voting, refinement, and custom multi-model deliberation.

1

scvd.store

seancrecord

scvd.store is an evidence observatory for agentic commerce. Independent signed observation of what other people's endpoints, artifacts and payments actually did among other things. USDC on Base, Arbitrum One, World Chain

2

CrawlForge MCP Server

mysleekdesigns

28-tool MCP server for web scraping, crawling, deep research & autonomous extraction — clean Markdown & structured JSON for Claude, Cursor & any MCP client. 1,000 free one-time credits, local-Ollama LLM support.

2
广告合作