avoid-ai-writing-mcp

A local, deterministic MCP server for auditing prose with the published avoid-ai-writing-detector.

It exposes two read-only tools:

• score_text returns a compact score, classification, confidence, and counts.

• audit_text adds every flagged pattern, suggested alternatives, statistics, and highlighted sentence regions.

The server makes no network calls and uses no language model. Text stays inside the local MCP process. Scores are heuristic writing-pattern signals, not proof that a person or model wrote the text.

Requirements

• Node.js 18 or newer

• An MCP host that supports local stdio servers

Related MCP server: Byakugan: Private, open-source AI-text checker

Run from GitHub

Add this server to Claude Code:

claude mcp add avoid-ai-writing -- npx -y github:conorbronsdon/avoid-ai-writing-mcp

Or add it to an MCP JSON configuration:

{
  "mcpServers": {
    "avoid-ai-writing": {
      "command": "npx",
      "args": ["-y", "github:conorbronsdon/avoid-ai-writing-mcp"]
    }
  }
}

After the package is released to npm, replace the GitHub package spec with avoid-ai-writing-mcp.

The package uses stdio for protocol messages. It does not open a port or send input to an API.

Tool inputs

Both tools accept:

technical mode reduces noise from patterns that are normal in code-adjacent writing. The other modes preserve the detector's context-specific behavior.

Development

npm install
npm test
npm run inspect

npm run inspect launches the official MCP Inspector against the local stdio entry point.

Scope

This package intentionally does not expose a rewrite tool. Rewriting requires editorial judgment and often a hosted model; adding that would undermine this server's deterministic, local, privacy-preserving contract.

License

MIT