Free, open-source MCP server that removes statistical text watermarks (ChatGPT, Claude, Gemini) with your own OpenRouter key
View on GitHub ↗Homepage ↗An open-source MCP server that removes statistical text watermarks, the kind ChatGPT, Claude and Gemini put into the text they write, by rewriting the wording while keeping the meaning, the structure and the formatting. It runs on your computer and talks only to OpenRouter with your own key, on OpenRouter's free models, so it costs nothing. The price is speed, consistency and availability: on 2026-10-05 the free model that answered took one to three and a half minutes and replaced 70%, 70% and 87% of the wording on three runs of one text (this tool's target is 80%), and free models are withdrawn without notice. The server tries several of them in order.
Works in Claude Desktop, Claude Code, Codex, Cursor and any other MCP client.
Prefer not to deal with keys and installs? Use the hosted version at painintheagent.com The same rewrite as a connector for claude.ai (it works in the browser and on phones, where a local MCP server cannot run) and as a web tool, plus an AI Humanizer and detectors. It answers in 2 to 10 seconds on a paid model and needs no OpenRouter account: three free runs, then $10 a month for 100,000 characters. Remote MCP URL: https://painintheagent.com/mcp · API & MCP docs
1. Masks the parts that must come back untouched: web links, email addresses, quoted spans, currency amounts and percentages. 2. Sends the masked text to the model with one instruction set: rewrite every sentence with a different construction and word order; keep every term, name, number and the layout; keep the strength of every statement (should is not must, 17.5% is not up to 17.5%);
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/balakhonoff--claude-watermark-remover.html)
runs anywhere. uses anything
illiahaidar/mcptrustcheckerMCP security scanner — offline, deterministic A–F Trust Score for Model Context Protocol servers. Detects tool poisoning, prompt injection & toxic flows.
yearningss/gamemaker-mcpA powerful, project-aware Model Context Protocol (MCP) server for GameMaker Studio with 190 tools, GML static analysis, refactoring, and automated builds.
slxca/opencontextA Model Context Protocol server for persistent project-specific AI agent context.
zaber-dev/free-ai-gatewayEnterprise-grade capability-driven AI routing engine, proxy gateway, MCP server, developer CLI, and agentic skills aggregator for 19+ free-tier AI providers.
Brokenwatch24/crowdmindDesktop app for building AI persona panels and testing stimuli against them (Electron + React + TypeScript)
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.