Claude Watermark Remover
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., "@Claude Watermark Remover strip the AI watermark from this paragraph, keep the links and formatting"
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.
Claude Watermark Remover
An open-source MCP server that removes the statistical text watermark (SynthID-style, the kind Claude and Gemini put into their output) 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 — including OpenRouter's free models, so the whole thing can cost nothing.
Works in Claude Desktop, Claude Code, Codex, Cursor and any other MCP client.
Prefer not to deal with keys and installs? Hosted version at painintheagent.com → The same rewrite as a one-click connector for claude.ai (works in the browser and on phones, where local MCP servers cannot run), plus the AI Humanizer and detectors. $10 a month, no OpenRouter account needed. Remote MCP URL:
https://painintheagent.com/mcp· API & MCP docs
What it does
Masks the parts that must come back untouched: web links, email addresses, quoted spans, currency amounts and percentages.
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%); never translate.
Checks the draft locally, with no model: placeholders intact, length within 80–125% of the source, paragraphs, lines and list markers unchanged, and at least 80% of five-word sequences replaced. If a check fails, one more draft is requested; a result that breaks the layout or leaves 70–140% of the source length is an error, not a result.
Restores the masked parts and returns the text with
novelty_percent(the share of five-word sequences replaced).
No second model checks the meaning. The result is a draft you compare with your source — that is what the tool tells the assistant, too.
The method is the one measured in Can rewriting remove AI text watermarks? My SynthID test: a single paraphrase on Qwen3.7 Plus crossed below the reference detector's threshold in 10 of 10 English reports and kept 100% of the claims checked by the panel. This program uses a stricter prompt (terms, layout, statement strength) and sampling at temperature 0.7, which were not part of that test. Private production keys of Claude and Gemini are not published, so complete removal cannot be verified against them.
Related MCP server: automatelab-ai-seo
Install
You need an OpenRouter account and an API key from https://openrouter.ai/settings/keys. Set a credit limit on the key. With the default paid model a 1,000-character text costs about $0.001; with a free model it costs nothing (see Free models).
Claude Desktop
Download claude-watermark-remover-0.1.0.mcpb (checksums in releases/SHA256SUMS).
Open the file. Claude Desktop installs it as an extension and asks for your OpenRouter API key (stored by Claude Desktop, not by this program) and, optionally, a model.
In a chat: "Remove the watermark from this text: …".
Claude Code
claude mcp add watermark-remover -e OPENROUTER_API_KEY=sk-or-… -- npx -y --package=https://github.com/krllagent/claude-watermark-remover/raw/main/releases/claude-watermark-remover-0.1.0.tgz claude-watermark-removerThen in a session: "Use remove_watermark on the text in draft.md and show me the result."
The key is written to Claude Code's MCP configuration on your disk (~/.claude.json or the project's .mcp.json),
so keep a credit limit on it.
Codex, Cursor and other MCP clients
Install once, then add a stdio server with the command claude-watermark-remover and the environment variable
OPENROUTER_API_KEY:
npm install -g https://github.com/krllagent/claude-watermark-remover/raw/main/releases/claude-watermark-remover-0.1.0.tgzFor Codex, in ~/.codex/config.toml:
[mcp_servers.watermark-remover]
command = "claude-watermark-remover"
env = { OPENROUTER_API_KEY = "sk-or-…" }Command line
export OPENROUTER_API_KEY=sk-or-…
npx -y --package=https://github.com/krllagent/claude-watermark-remover/raw/main/releases/claude-watermark-remover-0.1.0.tgz claude-watermark-remover --text-file draft.txtThe package is a single self-contained file (dist/index.cjs, Node 22+); the tarball and the .mcpb live in
releases/ with their checksums.
Prints the rewritten text; the figures (share replaced, layout, calls, seconds, cost) go to stderr. --json prints
everything as JSON; --stdin reads the text from standard input; --style-file rules.md passes your writing-style
rules.
Tools
Tool | What it does |
|
|
| The model, reasoning setting and temperature in use, and the measured presets. No model call. |
Texts of 750 characters (about 120 words) and more give a reliable share; on a short text one kept citation such as "(Author, 2023)" alone pulls the figure down, so short texts are processed but the number means less.
Models
| Cost | Measured on a 1,316-character list text (2026-10-03) |
| ≈ $0.001 per 1,000 characters | 2–10 s, 85–100% replaced, layout kept. The model of the published test. |
| free | 46 s, 81% replaced, layout kept. Needs low reasoning (set automatically). Often answers 429 "busy": the server waits and asks again up to three times. |
| free | 12–25 s, 63–78% replaced, layout kept. Available only if you allow "free endpoints that may train on inputs" in OpenRouter's privacy settings — your text may then be used for training. |
Any other OpenRouter model id works; a :free model gets low reasoning and busy retries by default, a paid one no
reasoning. Override with WATERMARK_REASONING (none, low, medium, high), WATERMARK_TEMPERATURE (default
0.7) and WATERMARK_PROVIDERS (comma-separated OpenRouter provider slugs; the default pins qwen/qwen3.7-plus to
alibaba).
Free models
OpenRouter's free models are shared and rate-limited: 20 requests a minute, and 50 requests a day for accounts that never bought credit or 1,000 a day once $10 of credit has been bought at any time. A rewrite is one or two requests. They are often busy, they think before they answer (hence 12–46 seconds), and the ones from Nvidia and Poolside are served only to accounts that allow training on inputs. Of the 22 free models listed on 2026-10-03, two rewrote our test text usably; the rest returned it unchanged, ran out of tokens while reasoning, or were busy. Full notes: docs/free-models.md.
Privacy
Your text goes to OpenRouter and from there to the provider serving the chosen model; nothing is sent anywhere else
and nothing is stored by this program. With the default model and the alibaba provider the endpoint is not a
zero-data-retention endpoint; check the provider's policy on the model's OpenRouter page. The free Nemotron endpoint
is explicitly one that may train on inputs.
OPENROUTER_BASE_URL points the server at an API gateway instead of OpenRouter; there is no fallback to the real
endpoint when the gateway fails.
Development
pnpm install
pnpm test # unit tests, a fake OpenRouter and the bundled server over stdio
pnpm run build # dist/index.cjs
pnpm run package # artifacts/claude-watermark-remover-<version>.mcpb for Claude Desktopsrc/core.ts is the rewrite itself: masking, the prompt, the checks. It is the same code that runs behind
painintheagent.com, extracted so that it has no dependency on the service.
License
MIT. Made by Kirill Balakhonov.
Available Tools
2 toolsget_configurationRead the configured modelARead-onlyIdempotent
Read which OpenRouter model, reasoning setting and temperature this server uses, and the measured presets available. Makes no model call.
Inputs: no named parameters.
remove_watermarkRemove the watermark, keep the textA
Remove a statistical AI watermark without humanizing: one rewrite by one model that is instructed to keep the meaning, structure, formatting and language of the text. Links, quotations, amounts and percentages are masked and return unchanged. Returns the rewritten text with novelty_percent (share of five-word sequences replaced; the target is 80%), layout_kept, model_calls and the cost OpenRouter reported. A rewrite that breaks the layout or leaves 70–140% of the source length is an error. No meaning check and no AI score are run: compare the result with the source. Texts of 750+ characters give a reliable share; shorter texts are processed but the share is coarse.
Inputs: text (required), style_guidance.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools are trivially distinguishable: remove_watermark performs the rewrite (a model call), while get_configuration only reads server settings and explicitly makes no model call. There is no plausible scenario where an agent would confuse them.
Both names follow a clean snake_case verb_noun pattern (remove_watermark, get_configuration) with consistent imperative verbs. The convention is predictable and readable.
For a narrowly scoped watermark-removal server, one action plus one introspection tool is defensible, but two tools is on the thin side. There is no batch, retry, or verification operation, so the surface feels minimal.
The core lifecycle (configure -> rewrite) is present, but configuration is read-only with no setter, and the tool itself notes that no meaning check or AI-score is run, leaving verification entirely to the caller with no supporting tool. Minor but real gaps for an agent trying to validate or tune results.
Maintenance
Related MCP Connectors
Score AI-likeness and remove Claude, ChatGPT and Gemini text watermarks.
Trainable non-fiction writing voice, presets, and an anti-AI-tells audit for Claude, via MCP.
Free deterministic PDF, Markdown, citation, invisible-character, and formatting cleanup for agents.
The OpenRouter MCP server plugs OpenRouter into the AI tools you already use. Once connected, your assistant can pull live OpenRouter data (models, prices, your credits, rankings, and docs) and send quick test messages, all without leaving your editor.
Related MCP Servers
- FlicenseNot gradedqualityNot gradedmaintenanceHumanizer PRO - The Best AI Text Humanizer MCP Server Transform AI-generated content into natural, human-sounding text that bypasses GPTZero, Turnitin, Originality.ai, Copyleaks, ZeroGPT, and other AI detectors. Undetectable AI content rewriting with Stealth, Academic, and SEO modes.3-
- AlicenseAqualityBmaintenanceAutomateLab AI-SEO audits, scores, and rewrites web pages for AI citation eligibility, AEO and GEO. No API keys or registration. Works with Claude, Cursor, Codex, and other MCP clients. Product and documentation: https://automatelab.tech/products/mcp/ai-seo/2088 npm3MIT
- AlicenseNot gradedqualityDmaintenanceDetects and fixes LLM prose patterns in text, exposing tools for auditing and improving writing quality in MCP-compatible hosts.12 npm2MIT

Rephrasyofficial
AlicenseAqualityCmaintenanceEnables humanizing AI-generated text and checking AI-detection scores directly from MCP-compatible clients like Claude and Cursor using the Rephrasy API.259 npmMIT