Recall Risk

com.dropwatchhqPublished by dropwatchhq.comOfficial publisherv1.0.0Updated Oct 25, 2026

Check a product's recall risk: score + active CPSC/FDA/NHTSA recalls for a product or brand.

The publisher's own server: Agent Receipts

VerifiedStreamable HTTPWeb executableData & AnalyticsBusiness & Commerce

Overview

AI-generated overview

A remote MCP server that gives an assistant a 0-100 recall-risk signal for a tracked product, brand or model, based on public complaint data.

What you can do
Look up the current complaint-velocity recall-risk signal for a tracked product, brand or model, returning a 0-100 score and risk band, complaint velocity and acceleration, and severe-hazard share.
When to use it
Useful when you want a quick, data-driven read on product safety complaints for a brand or model, for example during sourcing, purchasing or market research. It is a risk signal, not an official recall notice.
Requirements
A remote streamable HTTP endpoint; no package, environment variables or headers are declared. The manifest declares no authentication.
Before you install
The score is derived from public complaint data and is explicitly not an official recall or a claim that a product is defective; treat it as one indicator only. The registry description also mentions active CPSC/FDA/NHTSA recalls, but the listed tool returns only the risk signal, so verify official recall status separately.

Installation

In SourceWeft

  1. Open Recall Risk in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.dropwatchhq%2Frecall-risk/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "recall-risk": {
      "type": "http",
      "url": "https://cassandra.dropwatchhq.com/mcp"
    }
  }
}

Tools

1

recall_risk

Get the current complaint-velocity recall-risk signal for a tracked product/brand/model. Returns a 0-100 risk score, band, complaint velocity & acceleration, and severe-hazard share. This is a RISK SIGNAL from public complaint data, NOT an official recall or a claim the product is defective.

Parametersentityrequired

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

72% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts

    Publish an icon in the registry entry.

  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.

Other Dropwatchhq integrations