Draft revision
Rewrite stiff passages during an active drafting session, then ask the assistant for a side-by-side editorial review.
MCP integration
AI Humanizer MCP for Claude, ChatGPT, and Codex
Rewrite supplied text inside your assistant, with automatic OAuth for hosted connectors and the active task still in context.
Hosted connectors need only the MCP URL and your Detecting AI sign-in. The install prompt remains available for clients that read a local MCP config and use an API key.
Hosted connector details
MCP URL
https://api.detecting-ai.com/api/mcp
Hosted authentication
OAuth 2.0 — sign in and approve in your browser
Tools
humanize_text, detect_ai_textWhat 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.
- 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 one account balanceOAuth connectors and local API-key clients use the same humanizer word balance from your Detecting AI API subscription.
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
Hosted connectors discover OAuth automatically. Local clients can use the same Streamable HTTP endpoint with an API key in the Authorization bearer header.
Claude CodeConnect once and call the humanizer while drafting or reviewing text.
CodexUse the MCP server during documentation and content workflows.
ClaudeAdd a custom connector and sign in to Detecting AI with OAuth.
ChatGPTEnable Developer Mode, add the MCP URL, and sign in with OAuth.
Connect from Claude or ChatGPT
Add Detecting AI as a custom connector and paste the public MCP URL. The client will open Detecting AI so you can sign in, review the requested permission and word-usage notice, and approve or decline the connection. You never need to copy an API key into a hosted connector.
- Open the client's connector settings. ChatGPT users must enable Developer Mode before adding a custom connector.
- Paste
https://api.detecting-ai.com/api/mcpas the connector URL. - Sign in to Detecting AI and approve the connection.
Public MCP endpoint
https://api.detecting-ai.com/api/mcpDo not append an API key, OAuth token, or any other credential to this URL.
Where AI Humanizer MCP fits
MCP works best when the assistant needs a focused external tool as part of a user-controlled workflow.
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
For Codex and other local-config clients, store your Detecting AI API key in an environment variable. Codex reads the bearer token from the named variable.
Public MCP endpoint
https://api.detecting-ai.com/api/mcpCodex 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 = 180AI 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, ChatGPT, and Codex?
Yes. Hosted Claude and ChatGPT connectors use OAuth, while Claude Code and Codex can connect with a 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
Paste the public MCP URL into a hosted connector and sign in, or use an API key from a local MCP client.