Integration

Winston AI integration

Winston AI detects AI-generated content. Score a text for the likelihood it was written by an AI (with per-sentence scores), check whether an image was generated by AI (a standard check or an advanced forensic report), scan a text or web page for plagiarism across the internet, fact-check the claims in a text against trusted sources, and compare two texts for overlap. Every call spends credits from the account: 1 per word for AI text detection, 2 per word for plagiarism and fact checking, 300 per image, 500 per advanced image analysis, half a credit per word for text compare. The superseded v1 routes are not exposed (the v2 tools cover them). Authentication is a Bearer token created in the Winston AI developer dashboard.

Connect Winston AI How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

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

What you can do with Winston 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.

Ai image detection, 1 operation

detect_ai_imageDetect ai imagePOSTCheck whether an image was generated by AI, from a public image URL or base64 data (pass one of url or image). Returns a human score 0 (AI) to 100 (human), probabilities, C2PA and EXIF metadata. Costs 300 credits.

Ai text detection, 1 operation

detect_ai_textDetect ai textPOSTScore how likely a text, a public document (.pdf, .doc, .docx) or a web page was written by AI. Returns a human score 0 (AI) to 100 (human) and per-sentence scores. Costs 1 credit per word.

Fact check, 1 operation

check_factsCheck factsPOSTFact-check the claims in a text, a public document (.pdf, .doc, .docx) or a web page against trusted sources. Returns each claim with a verdict, confidence score, explanation and source links. Costs 2 credits per word.

Image forensics, 1 operation

analyze_image_forensicsAnalyze image forensicsPOSTRun an advanced forensic analysis on a public image URL: a label, confidence, authenticity verdict, conclusion and per-tool findings (metadata, classification, error level analysis). Costs 500 credits per image.

Plagiarism scan, 1 operation

check_plagiarismCheck plagiarismPOSTCheck a text, a public document (.pdf, .doc, .docx) or a web page for plagiarism against content found on the internet. Returns a plagiarism score, matching sources and the copied sequences. Costs 2 credits per word.

Text comparison, 1 operation

compare_textsCompare textsPOSTCompare two texts and measure their overlap. Returns an overall similarity score 0 to 100 and, for each text, the word counts, matching percentage and the matching segments. Costs half a credit per word in both texts.

Use Winston AI from Claude Code, Cursor or Codex

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

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