Integration

GPTZero integration

GPTZero detects AI-generated writing. Scan a text or uploaded files and get back the probability that the document is human, AI or mixed, with a score for each paragraph and each sentence; run a bibliography scan that checks whether each citation in a document exists; list the detector model versions you can pin; and read the words used and left in the current billing cycle. The streaming AI-patterns route (Server-Sent Events) is not exposed. Authentication is an API key, created on the API page of the GPTZero app and sent in the x-api-key header.

Connect GPTZero How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in GPTZero.Built from the 6 GPTZero tools below, on the connection you add once.

What you can do with GPTZero

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.

Citation, 2 operations

scan_bibliography_fileScan bibliography filePOSTRuns a bibliography scan on one uploaded file (a file from a previous step): finds its citations and claims, checks whether each cited work exists, and returns the sources it matched. The result is a list with one scan result, for the file.
scan_bibliography_textScan bibliography textPOSTScans the text of one document for citations and claims, checks whether each cited work exists (flagging possibly hallucinated citations), and returns the sources it matched.

File, 1 operation

detect_ai_in_fileDetect ai in filePOSTDetects AI in one uploaded file (a file from a previous step) and returns the scan result for it, with probabilities for the document, each paragraph and each sentence.

Model version, 1 operation

list_model_versionsList model versionsGETLists the detector model versions you can pass as modelVersion to detect_ai_in_text or detect_ai_in_file. The list can include versions that are not released yet.

Text, 1 operation

detect_ai_in_textDetect ai in textPOSTDetects AI in a single text input and returns probabilities for the document, each paragraph and each sentence.

Usage, 1 operation

get_usage_statsGet usage statsGETReturns how many words you have used and have left in the current billing cycle, and your plan.

Use GPTZero from Claude Code, Cursor or Codex

Connect GPTZero in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its GPTZero 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 GPTZero

Create your workspace
Sign up free. Nothing to install.
Connect GPTZero once
Add your GPTZero 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.