Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "openwarrant-aitext": {
      "type": "http",
      "url": "https://www.stipple.sh/mcp-aitext"
    }
  }
}

claude mcp add --transport http openwarrant-aitext https://www.stipple.sh/mcp-aitext

[mcp_servers.openwarrant-aitext]
url = "https://www.stipple.sh/mcp-aitext"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "openwarrant-aitext": {
      "type": "remote",
      "url": "https://www.stipple.sh/mcp-aitext",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "openwarrant-aitext": {
      "type": "http",
      "url": "https://www.stipple.sh/mcp-aitext"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=openwarrant-aitext&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vd3d3LnN0aXBwbGUuc2gvbWNwLWFpdGV4dCJ9"
}

{
  "servers": {
    "openwarrant-aitext": {
      "type": "http",
      "url": "https://www.stipple.sh/mcp-aitext"
    }
  }
}

{
  "mcpServers": {
    "openwarrant-aitext": {
      "httpUrl": "https://www.stipple.sh/mcp-aitext"
    }
  }
}

extensions:
  "openwarrant-aitext":
    enabled: true
    name: "openwarrant-aitext"
    type: streamable_http
    uri: "https://www.stipple.sh/mcp-aitext"
    timeout: 300

Quality 82 / 100good

protocol75 · weight 25

warn
protocol.modernnewest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
n/a
protocol.statelessonly applies to 2026-07-28 servers
pass
protocol.transportstreamable HTTP
n/a
protocol.list_ttlonly applies to 2026-07-28 servers

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene79 · weight 30

pass
tools.descriptionsevery tool has a description
warn
tools.description_length1 tools have descriptions over 1,024 characters, which crowds the context
pass
tools.schemasevery tool has an object input schema
pass
tools.annotations1 of 1 tools declare readOnlyHint or destructiveHint
fail
tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: detect_ai_text (destructiveHint, idempotentHint, openWorldHint)
pass
tools.token_costabout 377 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability100 · weight 15

pass
stability.changesno tool changes in 30 days
pass
stability.rug_pullno tool changed its meaning under the same name

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

1 tools, about 377 tokens to load them all · tool set 5009b1b72505 · checked 2026-10-20 19:42 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 89 / 100

duplicate-repo

provenance85

liveness100

freshness85

hygiene80

+repository +dns-namespace +website +reachable +uptime-100% ~updated-52d-ago -duplicate-repo(4 names)

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://www.stipple.sh/mcp-aitext` streamable-http	none	yes	100%	1168 ms	2025-11-25	2026-10-20

Tools (1)

detect_ai_textread-only 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.

Schemas: list_tools.

Also listed as

3 other active names share this repository: sh.stipple/openwarrant, sh.stipple/openwarrant-verify, sh.stipple/stipple-tenders

Similar MCP servers

More from sh.stipple

Official server.json

{
  "name": "sh.stipple/openwarrant-aitext",
  "title": "Stipple — AI Text Detection",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://www.stipple.sh/mcp-aitext",
      "type": "streamable-http"
    }
  ],
  "version": "0.1.7",
  "repository": {
    "url": "https://github.com/Sketchjar/stipple-mcp",
    "source": "github"
  },
  "websiteUrl": "https://www.stipple.sh/ai-detector",
  "description": "Is this prose AI-written? A probability with the tells behind it. Free to start, no key."
}