Integration

Undetectable AI integration

Undetectable AI rewrites AI-generated text so it reads as human-written (its Humanizer). Submit a text with a readability level, a purpose, a strength and a model, then fetch the humanized document by its id once processing is done, rehumanize a document once, list past documents and check the remaining word credits. The streaming (WebSocket), token-exchange, UI hand-over and file-upload routes are not exposed, and the AI Detector, which takes the key in the request body, is not part of this integration. Authentication is the API key from the developer portal, sent in the apikey header.

Connect Undetectable AI How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Undetectable AI.Built from the 5 Undetectable AI tools below, on the connection you add once.

What you can do with Undetectable AI

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Document, 4 operations

get_documentGet documentPOSTReturns a submitted document by id: the original input, the humanized output, readability, purpose and creation date. Call it every 5 to 10 seconds after submit_document until output is filled.
list_documentsList documentsPOSTLists your documents, 10 per page, newest first by creation date. When pagination is true there are more: call again with offset increased by 10.
rehumanize_documentRehumanize documentPOSTHumanizes an already submitted document again, replacing its previous humanization; allowed once per document. Returns an id: call get_document with it until output is filled. Consumes word credits.
submit_documentSubmit documentPOSTSubmits a text for humanization and returns its document id at once; the text is not processed yet. Call get_document with that id every 5 to 10 seconds until output is filled. Consumes word credits.

Credits, 1 operation

get_user_creditsGet user creditsGETReturns the remaining word credits of the account: base credits, boost credits and their total. Use it before submitting long texts.

Use Undetectable AI from Claude Code, Cursor or Codex

Connect Undetectable AI in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Undetectable AI operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Undetectable AI

Create your workspace
Sign up free. Nothing to install.
Connect Undetectable AI once
Add your Undetectable AI connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.