protogrid

Search / com.edgethirteen.www/cloakcheck

cloakcheck

not classified

Scan a page for content planted to hijack an AI browsing/shopping agent before it acts on the page.

v1.0.0 · active · website · descriptor JSON · versions

Not classified yet.The remote endpoints have not been probed successfully, or the listing has nothing to connect to.
Quality81good
Trust50of 100
Uptime, 30 days50%
Latency p50175 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "cloakcheck": {
      "type": "http",
      "url": "https://www.edgethirteen.com/api/mcp/cloakcheck"
    }
  }
}
claude mcp add --transport http cloakcheck https://www.edgethirteen.com/api/mcp/cloakcheck
[mcp_servers.cloakcheck]
url = "https://www.edgethirteen.com/api/mcp/cloakcheck"
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "cloakcheck": {
      "type": "remote",
      "url": "https://www.edgethirteen.com/api/mcp/cloakcheck",
      "enabled": true
    }
  }
}
{
  "mcpServers": {
    "cloakcheck": {
      "type": "http",
      "url": "https://www.edgethirteen.com/api/mcp/cloakcheck"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=cloakcheck&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vd3d3LmVkZ2V0aGlydGVlbi5jb20vYXBpL21jcC9jbG9ha2NoZWNrIn0%3D"
}
{
  "servers": {
    "cloakcheck": {
      "type": "http",
      "url": "https://www.edgethirteen.com/api/mcp/cloakcheck"
    }
  }
}
{
  "mcpServers": {
    "cloakcheck": {
      "httpUrl": "https://www.edgethirteen.com/api/mcp/cloakcheck"
    }
  }
}
extensions:
  "cloakcheck":
    enabled: true
    name: "cloakcheck"
    type: streamable_http
    uri: "https://www.edgethirteen.com/api/mcp/cloakcheck"
    timeout: 300

Quality 81 / 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 hygiene86 · weight 30
  • pass
    tools.descriptionsevery tool has a description
  • pass
    tools.description_lengthdescriptions are concise
  • 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: check_page_for_agent_hijacking (idempotentHint)
  • pass
    tools.token_costabout 217 tokens to load every tool
  • pass
    tools.api_dumptools are not a one-to-one API dump
stabilityn/a · weight 15
  • n/a
    stability.changes, stability.rug_pulltool history not recorded yet
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

1 tools, about 217 tokens to load them all · checked 2026-10-20 17:02 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 50 / 100

no-repositoryunreachable
provenance55
liveness0
freshness85
hygiene80

+dns-namespace +website -unreachable(12 failures) ~updated-37d-ago -no-repository

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

Endpoints

remoteauthreachableuptime 30dp50protocollast ok
https://www.edgethirteen.com/api/mcp/cloakcheck streamable-httpnoneno (12 failures)50%175 ms2025-11-252026-09-23

Tools (1)

check_page_for_agent_hijackingread-onlyFetch a URL and scan it for content planted to hijack an AI agent visiting it rather than to inform a human: invisible unicode (zero-width joiners, steganographic tag-block characters), CSS-hidden text (display:none, opacity:0, off-screen) paired with instruction-shaped language ('ignore previous instructions', 'add to cart and checkout', fake system-role text), and instruction-shaped phrases in alt/title/aria-label attributes or meta tags. Call this before an autonomous browsing or checkout flow acts on instructions found on a page. A clean result means no known hijack pattern found, not a full content-safety guarantee.

Schemas: list_tools.

Similar MCP servers

More from com.edgethirteen.www

And 28 more from this publisher.

Official server.json
{
  "name": "com.edgethirteen.www/cloakcheck",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://www.edgethirteen.com/api/mcp/cloakcheck",
      "type": "streamable-http"
    }
  ],
  "version": "1.0.0",
  "websiteUrl": "https://www.edgethirteen.com/tools/cloakcheck",
  "description": "Scan a page for content planted to hijack an AI browsing/shopping agent before it acts on the page."
}