DeepRecall - Product Safety Intelligence is a remote MCP server that gives an AI agent 2 tools, among them get_data_sources, search_recalls. It answers at https://mcp.deeprecall.io/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 21 October 2026, succeeded.
Search 120,000+ recalled products from 8 global safety agencies using AI similarity.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
get_data_sources | Get information about available recall data sources. Returns a list of all supported regulatory agencies and their coverage. This is a free call that does not consume API credits. Returns: Dictionary with data sources and their descriptions |
search_recalls | Search for recalled products similar to your query. This tool searches DeepRecall's global product safety database using AI-powered multimodal matching. Provide a text description and/or product images to find similar recalled products. Use Inputs: content_description, image_urls, filter_by_data_sources, top_k, model_name, input_weights |
Every block below points at https://mcp.deeprecall.io/mcp. Pick your client and copy.
claude mcp add --transport http deeprecall-product-safety-intell https://mcp.deeprecall.io/mcp
{
"mcpServers": {
"deeprecall-product-safety-intell": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.deeprecall.io/mcp"]
}
}
}{
"mcpServers": {
"deeprecall-product-safety-intell": {
"url": "https://mcp.deeprecall.io/mcp"
}
}
}{
"servers": {
"deeprecall-product-safety-intell": {
"type": "http",
"url": "https://mcp.deeprecall.io/mcp"
}
}
}{
"context_servers": {
"deeprecall-product-safety-intell": {
"url": "https://mcp.deeprecall.io/mcp"
}
}
}{
"mcpServers": {
"deeprecall-product-safety-intell": {
"serverUrl": "https://mcp.deeprecall.io/mcp"
}
}
}{
"mcpServers": {
"deeprecall-product-safety-intell": {
"url": "https://mcp.deeprecall.io/mcp"
}
}
}name: DeepRecall - Product Safety Intelligence
version: 0.0.1
schema: v1
mcpServers:
- name: DeepRecall - Product Safety Intelligence
type: streamable-http
url: https://mcp.deeprecall.io/mcp{
"mcpServers": {
"deeprecall-product-safety-intell": {
"httpUrl": "https://mcp.deeprecall.io/mcp"
}
}
}{
"mcpServers": {
"deeprecall-product-safety-intell": {
"type": "http",
"url": "https://mcp.deeprecall.io/mcp"
}
}
}{
"mcpServers": {
"deeprecall-product-safety-intell": {
"url": "https://mcp.deeprecall.io/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fmcp.deeprecall.io%2Fmcp&type=streamable_http&id=deeprecall-product-safety-intell&name=DeepRecall%20-%20Product%20Safety%20Intelligence
It answered our last check on 21 October 2026 in 599 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
2, as returned by the server's own tools/list on 13 September 2026: get_data_sources, search_recalls.
It answered our last check on 21 October 2026 in 599 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp.deeprecall.io/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.adrida. Endpoint host: mcp.deeprecall.io. ARD identifier: urn:air:io.github.adrida:mcp:deeprecall-mcp.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.