ReverseGPT

Connect ReverseGPT to Claude and ChatGPT

One endpoint turns any MCP client into an AI humanizer. Your assistant rewrites AI-generated text as a tool call, using your existing plan and credits.

Server URL https://www.reversegpt.ai/api/mcp

Streamable HTTP. OAuth 2.1 with dynamic client registration and PKCE, or an API key header — whichever your client prefers.

Tools

Two tools, one job. ReverseGPT does one thing through MCP — it humanizes text — and the second tool exists only to collect a run that outlasted its call.

Tool	What it does	Arguments	Cost
humanize_text humanize:write	Rewrite AI-generated text so it reads as human-written while keeping its meaning. Up to 1000 words per call. Credit-based plans use one credit per input word; Max includes the run. Waits briefly, then returns either the rewrite or a job id to poll.	text ultra (Max plan only — a second rewriting pass)	1 credit / word
get_humanize_job humanize:read	Read the status and result of an existing run, including a completed run. Polling costs nothing.	jobId	Free

A humanize_text call, end to end

// What the assistant sends
{
  "name": "humanize_text",
  "arguments": {
    "text": "The utilization of advanced methodologies facilitates optimal outcomes."
  }
}

// What comes back
{
  "jobId": "clx8k2p9a0001",
  "status": "completed",
  "done": true,
  "wordCount": 9,
  "ultra": false,
  "humanizedText": "Using better methods gets you better results.",
  "wordsProcessed": 9,
  "chunkCount": 1,
  "nextStep": "Done. \`humanizedText\` is the rewritten text — return it to the user as it is."
}

Connect it

Claude (web, desktop, mobile)

Settings → Connectors → Add custom connector, then paste the endpoint URL. Claude runs the OAuth flow and you sign in with your ReverseGPT account — no key to copy.

Claude Code

Run the CLI command below. It registers the server for the current project and handles the OAuth handshake on first use.

ChatGPT

Settings → Connectors → Add, then paste the endpoint URL. ChatGPT registers itself and runs the same OAuth flow.

Cursor, Windsurf, Zed and other MCP clients

Add the JSON block below to the client's MCP config. These clients generally want a header credential, so use an API key from Settings.

Claude Code

claude mcp add --transport http reversegpt https://www.reversegpt.ai/api/mcp

mcp.json — key-based clients

{
  "mcpServers": {
    "reversegpt": {
      "type": "http",
      "url": "https://www.reversegpt.ai/api/mcp",
      "headers": {
        "Authorization": "Bearer rg_live_YOUR_KEY"
      }
    }
  }
}

How it behaves

It asks before it spends

A humanize call creates a job and can debit credits, so the tool is advertised as readOnlyHint: false. Clients can use this to request approval. Credit-based plans use one credit per input word; Max does not debit credits.

It keeps your job in progress

humanize_text waits briefly for a result. If the rewrite is still running, it returns a job id and continues in the background. The assistant uses that same id with get_humanize_job collects the result for free.

It is stateless

No session id, nothing retained between requests, and Origin validated on every connection. Up to 1000 words per call — the assistant splits longer drafts and runs the parts.

Frequently asked questions

What is the ReverseGPT MCP server?

It is an implementation of the Model Context Protocol at https://www.reversegpt.ai/api/mcp. Connecting it gives an AI assistant a humanize_text tool, so it can rewrite AI-generated text so it reads as human-written without you leaving the conversation.

Which AI clients can connect to it?

Any MCP client that speaks Streamable HTTP — Claude on web, desktop and mobile, Claude Code, ChatGPT, Cursor, Windsurf, Zed, and anything built on the MCP SDKs. Claude and ChatGPT sign in with OAuth; other clients use an API key header.

How do I authenticate?

Two ways. Claude and ChatGPT run an OAuth flow, so you just sign in with your ReverseGPT account and never handle a key. Any other client sends an API key from Settings as an Authorization: Bearer header.

What does it cost to use through an assistant?

Credit-based plans use one credit per input word; Max includes humanization without debiting credits. Reading a job back is free. Because humanize_text creates a job and can spend credits, it is marked as not read-only so clients can request approval.

Does the assistant see my text?

Only the text you give it. The tool sends that text to ReverseGPT, gets the rewrite back, and returns it to the conversation — the same path the editor uses. Nothing else in your account is exposed: the server has exactly two tools and neither can read your documents.

What happens if a rewrite takes a long time?

humanize_text waits briefly, then returns either the finished text or a job id with done: false. The rewrite continues in the background while the assistant polls get_humanize_job with that same id for free. If a connection fails before an id is received, do not automatically submit the text again: the original run may already exist.