This server provides local, deterministic, read-only AI-writing pattern analysis for prose, without network calls or language models.
score_text: Returns a compact 0–100 pattern score, classification (e.g., HUMAN_ONLY, MIXED, AI_ONLY), confidence, probabilities, word count, and issue count.
audit_text: Returns the score plus up to 100 flagged pattern issues with suggestions, up to 100 highlighted sentence regions, statistics, and truncation counts.
Context modes: Supports general, technical, marketing, and personal contexts; technical suppresses code-adjacent writing patterns.
Local & private: Text stays inside the local MCP process; no API calls and no hosted model are used.
Input limits: Accepts up to 100,000 characters per request.
Read-only: Both tools are read-only and do not rewrite or modify text.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@avoid-ai-writing-mcp Can you check this text for AI writing patterns?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Maintenance mode. This project is stable and receives security fixes. New features aren't planned, but issues and pull requests are still welcome.
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 a bounded set of flagged patterns, 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.
Node.js 20 or newer
An MCP host that supports local stdio servers
Related MCP server: slop-guard
Add this server to Claude Code:
claude mcp add avoid-ai-writing -- npx -y avoid-ai-writing-mcpOr add it to an MCP JSON configuration:
{
"mcpServers": {
"avoid-ai-writing": {
"command": "npx",
"args": ["-y", "avoid-ai-writing-mcp"]
}
}
}To run the current source directly from GitHub instead, use
github:conorbronsdon/avoid-ai-writing-mcp as the package spec.
The package uses stdio for protocol messages. It does not open a port or send input to an API.
Both tools accept:
Field | Type | Required | Description |
| string | yes | Text to evaluate locally (maximum 100,000 characters). |
| enum | no |
|
technical mode reduces noise from patterns that are normal in code-adjacent
writing. The other modes preserve the detector's context-specific behavior.
audit_text returns at most 100 issues and 100 highlighted regions. Its
truncated field reports how many additional items the detector produced.
npm install
npm test
npm run inspectnpm run inspect launches the official MCP Inspector against the local stdio
entry point.
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.
MIT
Audit text locally with the deterministic Avoid AI Writing detector. Returns the score plus up to 100 flagged patterns and 100 highlighted sentence regions, with truncation counts. This is a heuristic writing audit, not proof of authorship; use score_text for a compact result.
Inputs: text (required), context. Returns: label, score, issues, context, +10 more
Score text locally with the deterministic Avoid AI Writing detector. Returns a compact 0-100 pattern score, classification, confidence, and counts. This is a heuristic signal, not proof of authorship; use audit_text when individual findings are needed.
Inputs: text (required), context. Returns: label, score, context, scorable, +6 more
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 2 tools
score_text and audit_text have clearly separated purposes: one returns a compact classification while the other returns detailed flagged patterns and highlighted regions. The cross-references in the descriptions remove any real ambiguity about which tool to use.
Both tool names follow the same verb_noun pattern with lowercase snake_case and concise action words. This is fully consistent and predictable.
Two tools is slightly below the typical 3-15 range, but for a narrowly scoped local text detector the pair covers both a compact score and a detailed audit. Each tool has a distinct, useful role, so the small count feels intentional rather than inadequate.
The server's apparent domain is deterministic AI-writing detection on text, and the two tools cover the full user journey: getting a quick judgment or drilling into specific flagged patterns and highlighted regions. There are no obvious missing operations for this stated purpose.
Estimate how much of an English text or web page reads as AI-written. Read-only, two tools.
DraftCheck: flags AI-writing patterns in prose with fix hints. Deterministic linter, not a detector.
Scores whether a page reads as AI-generated and names the tells to fix.
Find AI-isms with evidence and fingerprint a writing voice from samples. 3 of 5 free.