MCP integration

AI Humanizer MCP for Claude and Codex

Rewrite supplied text inside your assistant while preserving the active task and context.

Claude Code MCP setup

claude mcp add --transport http --scope user \
  --header "Authorization: Bearer YOUR_API_KEY" \
  detecting-ai https://api.detecting-ai.com/api/mcp

What an AI Humanizer MCP server does

An AI Humanizer MCP server lets a compatible assistant send user-provided text to a focused rewriting tool. The result comes back to the same conversation, where the user can review, compare, or revise it without building a custom REST integration.

MCP documentation View the AI Humanizer API

Rewrite without context switchingHumanize selected text from the same Claude, Codex, or agent conversation where the draft is being reviewed.
Choose a supported modelSelect cognia, lexi, cognia_v2, or huma_v2 when the workflow needs a specific humanizer model.
Return editable textThe assistant receives the rewritten text, model name, and processed word count in a structured response.
Use existing API accessThe MCP tool uses the same API key and humanizer word balance as your Detecting AI subscription.

Detecting AI dashboard with the AI Humanizer tool selected

From draft to humanized text

The user supplies text and asks for a more natural rewrite. The client calls the Detecting AI humanizer tool with the chosen model. The server validates the subscription and word balance, processes the text, records usage, and returns a new version for review in the same conversation.

Available MCP tool

humanize_text: Rewrites user-supplied text in a more natural style and returns editable output.

Input	Type	Status	Description
`text`	string	Required	The text to rewrite.
`model`	string	Optional	Humanizer model. The default is cognia.

Compatible MCP clients

Connect through Streamable HTTP with an Authorization bearer header. Client support and configuration formats can vary by version.

Claude CodeConnect once and call the humanizer while drafting or reviewing text.

CodexUse the MCP server during documentation and content workflows.

Claude DesktopAdd a compatible remote MCP configuration for writing tasks.

Other agentsUse any Streamable HTTP client that can send a bearer header.

Where AI Humanizer MCP fits

MCP works best when the assistant needs a focused external tool as part of a user-controlled workflow.

Draft revision

Rewrite stiff passages during an active drafting session, then ask the assistant for a side-by-side editorial review.

Support content

Turn approved source material into clearer help content while keeping the result in the same agent workflow for review.

Content production

Humanize supplied marketing or educational drafts before the normal editing, fact-checking, and approval process.

Connect the humanizer to your assistant

Store your Detecting AI API key in an environment variable and configure the public MCP URL. Codex reads the bearer token from the named variable.

Public MCP endpoint
https://api.detecting-ai.com/api/mcp

Codex configuration

export DETECTING_AI_API_KEY="YOUR_API_KEY"

[mcp_servers.detecting_ai]
url = "https://api.detecting-ai.com/api/mcp"
bearer_token_env_var = "DETECTING_AI_API_KEY"
tool_timeout_sec = 180

AI Humanizer MCP questions

What is an AI Humanizer MCP server?

It is a remote MCP server that gives compatible assistants access to a dedicated text humanization tool through a standard protocol.

Which humanizer models are available?

The tool supports cognia, lexi, cognia_v2, and huma_v2. Cognia is the default for new calls.

Can I review the result before using it?

Yes. The humanized text is returned to the client as editable output. You should review it for meaning, facts, tone, and policy requirements.

Does it work with Claude and Codex?

Yes. Claude Code and Codex can connect to the public Streamable HTTP endpoint with your Detecting AI API key.

How is humanizer MCP usage counted?

Successful calls deduct the input word count from the same humanizer balance used by the Detecting AI REST API.

Use AI Humanizer from your AI client

Create an API key, connect the public MCP endpoint, and keep control of every tool call from the active conversation.

Get an API key Explore AI Detector MCP