Estimate the PROBABILITY that a document's text was AI-GENERATED (LLM-written prose). USE THIS WHEN someone shares prose — an essay, cover letter, article, review, application, or report (or a link to one) — and asks: did an AI / ChatGPT write this? is this human-written? detect AI text. Provide ...
AI agents call detect_ai_text to retrieve information from OpenWarrant without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
url | object | — | |
text | object | — | |
filename | string | — | |
bytes_b64 | object | — |
Parameters from the server's own tool schema.
The detect_ai_text tool is a document analysis and detection service that queries/inspects content to provide probabilistic insights. It does not create, modify, delete, execute code, move money, or trigger external side effects. The user provides a document, the tool analyzes it, and returns classification results.
From the tool's definition Tool analyzes and returns probability estimates about document text origin (AI-generated vs human-written).
Risk signalsAccepts file system path (filename) · Accepts URL/endpoint input (url)
Attacks that exploit this kind of access
Estimate the PROBABILITY that a document's text was AI-GENERATED (LLM-written prose). USE THIS WHEN someone shares prose — an essay, cover letter, article, review, application, or report (or a link to one) — and asks: did an AI / ChatGPT write this? is this human-written? detect AI text. Provide the document ONE way: text (pasted markdown/plain prose), url (a public http(s) link to a page or PDF — fetched server-side, the cheapest call), OR bytes_b64 (a base64 PDF/file, plus filename for routing). Returns {probability, lean, tells, reasoning, applicable}. HONEST SCOPE: the probability is the model's CONFIDENCE, not a calibrated truth — it can false-flag templated/coached or non-native-English writing. It works on PROSE only: for a form/table/numeric document (payslip, statement) it returns applicable: false and abstains, because AI-text detection false-positives badly there — use verify_document (the authenticity engine) for those, and verify_references to check a doc's citations/claims. It is categorised as a Read tool in the OpenWarrant MCP Server, which means it retrieves data without modifying state.
detect_ai_text accepts 4 parameters: url, text, filename, bytes_b64. The full parameter table on this page comes from the server's own tool schema.
Register the OpenWarrant MCP server in PolicyLayer and add a rule for detect_ai_text: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches OpenWarrant. Nothing to install.
detect_ai_text is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the detect_ai_text rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for detect_ai_text. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
detect_ai_text is provided by the OpenWarrant MCP server (https://www.stipple.sh/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →