protogrid

Search / com.dropwatchhq/safe-check

Safe-Check (recall + counterfeit)

R0· no sign-in

Is it recalled or fake? Recall lookup vs live US gov feeds + transparent counterfeit risk signal.

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

An agent can connect right now, no human step.Remote endpoint, no authentication, reachable on the last probe.
Quality79good
Trust75of 100
Uptime, 30 days97%
Latency p50159 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "safe-check": {
      "type": "http",
      "url": "https://safecheck.dropwatchhq.com/mcp"
    }
  }
}
claude mcp add --transport http safe-check https://safecheck.dropwatchhq.com/mcp
[mcp_servers.safe-check]
url = "https://safecheck.dropwatchhq.com/mcp"
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "safe-check": {
      "type": "remote",
      "url": "https://safecheck.dropwatchhq.com/mcp",
      "enabled": true
    }
  }
}
{
  "mcpServers": {
    "safe-check": {
      "type": "http",
      "url": "https://safecheck.dropwatchhq.com/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=safe-check&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vc2FmZWNoZWNrLmRyb3B3YXRjaGhxLmNvbS9tY3AifQ%3D%3D"
}
{
  "servers": {
    "safe-check": {
      "type": "http",
      "url": "https://safecheck.dropwatchhq.com/mcp"
    }
  }
}
{
  "mcpServers": {
    "safe-check": {
      "httpUrl": "https://safecheck.dropwatchhq.com/mcp"
    }
  }
}
extensions:
  "safe-check":
    enabled: true
    name: "safe-check"
    type: streamable_http
    uri: "https://safecheck.dropwatchhq.com/mcp"
    timeout: 300

Quality 79 / 100good

protocol75 · weight 25
  • warn
    protocol.modernnewest supported version is 2024-11-05; 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 hygiene71 · weight 30
  • pass
    tools.descriptionsevery tool has a description
  • pass
    tools.description_lengthdescriptions are concise
  • pass
    tools.schemasevery tool has an object input schema
  • fail
    tools.annotationsno tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
  • fail
    tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: counterfeit_risk (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); safe_check (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); recall_lookup (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
  • pass
    tools.token_costabout 342 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

3 tools, about 342 tokens to load them all · tool set 694fc94344ad · checked 2026-10-20 12:13 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 75 / 100

no-repository
provenance55
liveness99
freshness65
hygiene80

+dns-namespace +website +reachable +uptime-97% ~updated-120d-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://safecheck.dropwatchhq.com/mcp streamable-httpnoneyes97%159 ms2024-11-052026-10-20

Tools (3)

counterfeit_riskAssess counterfeit RISK for a collectible listing (a risk SIGNAL, never proof of fake). Combines marketplace base-risk + a price-vs-retail-median check when the item is a known collectible niche. Returns a risk level (low/med/high), a score, the signals, and authenticity advice.
recall_lookupLook up active US product recalls for a product or brand against live government feeds (CPSC/FDA/NHTSA-style aggregate). Returns matching recalls with the official agency source link and last-updated date. Use to check if something is recalled before buying/using it.
safe_checkRun both a recall lookup and a counterfeit-risk check in one call. Best general-purpose product-safety screen.

Schemas: list_tools.

Similar MCP servers

More from com.dropwatchhq

And 28 more from this publisher.

Official server.json
{
  "name": "com.dropwatchhq/safe-check",
  "_meta": {
    "io.modelcontextprotocol.registry/publisher-provided": {
      "sources": "CPSC/FDA/NHTSA-style recall aggregate + price-vs-retail counterfeit heuristic",
      "useCase": "Agents check product-safety: active recalls + a counterfeit RISK signal (never proof of fake)."
    }
  },
  "title": "Safe-Check (recall + counterfeit)",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://safecheck.dropwatchhq.com/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.0.0",
  "websiteUrl": "https://safecheck.dropwatchhq.com",
  "description": "Is it recalled or fake? Recall lookup vs live US gov feeds + transparent counterfeit risk signal."
}