Public MCP report
Stipple — AI Text Detection https://www.stipple.sh/mcp-aitext
Official Registry Official Registry · sh.stipple/openwarrant-aitext · Publisher namespace: sh.stipple
Server checked today at 20:36 UTC
Displayed catalog: last complete observation from September 19
1 public tool observed. Tools were not executed. These tools come from the catalog observation above, not from the latest availability check.
What Talandor observed
The server answered Add the endpoint to a compatible client below. A Watch can alert you if this public catalog changes.
This is a public protocol and tools/list check, not a functional validation.
https://www.stipple.sh/mcp-aitext
Availability Reachable measured
Tools 1 public tool observed measured
Compatibility Estimated from published client rules · not a hands-on test estimated
Configure your assistant · Check details
How to use this MCP Talandor checks the server; it does not connect the server to your assistant.
Choose your assistant, then copy the configuration shown for that client. Authentication is completed with the MCP provider, never inside Talandor.
Compatibility evidence by assistant Compatibility is estimated from published configuration rules and is not a hands-on test in each client.
Claude Observed 2025-11-25.
Likely compatible · inferred Cursor Streamable HTTP and public HTTPS were observed.
Likely compatible · inferred ChatGPT Public tool names, descriptions and schemas were observed. Plan and workspace access still apply.
Likely compatible · inferred VS Code Public remote HTTP configuration can be assessed.
Likely compatible · inferred Generic MCP Observed 2025-11-25.
Likely compatible · inferred Rule evidence: Remote HTTPS rule v0.2 · reviewed 2026-09-12 · Remote HTTP rule v0.2 · reviewed 2026-09-12 · Remote app rule v0.2 · reviewed 2026-09-12 · Protocol and transport rule v0.2 · reviewed 2026-09-12
Check details
What changed No earlier complete public snapshot yet. Watch would start a baseline on the next complete check.
Server-provided content. Tool names, descriptions and schemas below are copied from the MCP server. They may be in another language. Talandor does not translate or verify them.
Tools and declared exposure Server annotations are declarations, not verified behavior.
Show 1 of 1 server-provided tool definitions detect_ai_text
Declared read-only Show server-provided details Detect AI-written prose
Server description (copied; language not verified) 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.
Input schema (server-provided preview — do not copy) {
"type": "object",
"title": "detect_ai_textArguments",
"properties": {
"url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Url",
"default": null
},
"text": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Text",
"default": null
},
"filename": {
"type": "string",
"title": "Filename",
"default": "document.pdf"
},
"bytes_b64": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Bytes B64",
"default": null
}
}
}
Evidence and limitations Method: anonymous Streamable HTTP probe. We never invoke a tool.
Attempted protocols: 2026-07-28, 2025-11-25
Protocol 2025-11-25
Transport Streamable HTTP
Auth No authentication challenge observed
Evidence Public contract observed
Total latency 10775 ms
Response bytes 1765
No diagnostic errors.
Observation history Operational Sep 22, 2026 · 8:36 PM UTC
2025-11-25 · 1 tools Unreachable now Sep 22, 2026 · 7:51 PM UTC
No protocol Operational Sep 22, 2026 · 6:09 PM UTC · stable since Sep 22, 2026 · 5:22 PM UTC
2025-11-25 · 1 tools · no change · 2 checks Unreachable now Sep 22, 2026 · 11:53 AM UTC
No protocol Unreachable now Sep 22, 2026 · 7:21 AM UTC
No protocol Operational Sep 22, 2026 · 5:04 AM UTC
2025-11-25 · 1 tools Unreachable now Sep 22, 2026 · 3:44 AM UTC
No protocol Unreachable now Sep 22, 2026 · 2:21 AM UTC
No protocol Unreachable now Sep 22, 2026 · 1:08 AM UTC
No protocol Unreachable now Sep 21, 2026 · 10:29 PM UTC
No protocol Unreachable now Sep 21, 2026 · 9:14 PM UTC
No protocol Unreachable now Sep 21, 2026 · 7:53 PM UTC
No protocol Operational Sep 21, 2026 · 6:31 PM UTC
2025-11-25 · 1 tools Unreachable now Sep 21, 2026 · 3:32 PM UTC
No protocol Unreachable now Sep 21, 2026 · 2:11 PM UTC
No protocol Unreachable now Sep 21, 2026 · 12:50 PM UTC
No protocol Operational Sep 21, 2026 · 11:33 AM UTC
2025-11-25 · 1 tools Unreachable now Sep 21, 2026 · 10:10 AM UTC
No protocol Unreachable now Sep 21, 2026 · 8:50 AM UTC
No protocol Unreachable now Sep 21, 2026 · 7:30 AM UTC
No protocol Unreachable now Sep 21, 2026 · 6:09 AM UTC
No protocol Unreachable now Sep 21, 2026 · 4:49 AM UTC
No protocol Operational Sep 21, 2026 · 3:28 AM UTC
2025-11-25 · 1 tools Unreachable now Sep 21, 2026 · 2:08 AM UTC
No protocol Unreachable now Sep 21, 2026 · 12:48 AM UTC
No protocol Unreachable now Sep 20, 2026 · 11:28 PM UTC
No protocol Operational Sep 20, 2026 · 9:58 PM UTC
2025-11-25 · 1 tools Unreachable now Sep 20, 2026 · 7:33 PM UTC
No protocol Unreachable now Sep 20, 2026 · 6:03 PM UTC
No protocol Unreachable now Sep 20, 2026 · 3:39 PM UTC
No protocol Sep 19, 2026 · 7:48 AM UTC Complete public contract · 2025-11-25 · 1 tools
e15a4fa31801
Deep monitoring eligibility Eligible for deep monitoring
A complete public tools/list contract was observed, so a future deep-monitoring baseline can be compared safely.
Personal Watch is not open yet. This report does not start a Watch or a payment.
See public monitoring
Automatic monitoring later Saving this connector does not start a Watch. Watch is a future offer ; subscriptions and alerts are not available yet.
Full Watch. Availability, protocol, auth and public tool contract changes can be compared.