DeepRecall - Product Safety Intelligence

io.github.adridaPublished by GitHub account adridav1.0.0Updated Nov 2, 2026

Search 120,000+ recalled products from 8 global safety agencies using AI similarity.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingBusiness & Commerce

Overview

AI-generated overview

Searches a global product recall database by text or image so an assistant can check whether a product has been recalled.

What you can do
  • Search recalled products by text description and/or up to 10 product image URLs, with AI similarity matching
  • Filter results by regulatory agency and set how many results to return
  • List the supported recall data sources and their coverage
When to use it
Useful for pre-purchase safety checks, product compliance or sourcing research, and agentic commerce flows where an assistant should verify a product against recall notices from US, EU, UK, Canadian, French, Australian and international agencies.
Requirements
Remote MCP endpoint at mcp.deeprecall.io over streamable HTTP, or self-hosting with Python and pip. Requires a DeepRecall API key sent in the X-API-Key header (or DEEPRECALL_API_KEY when self-hosting). Access is currently closed beta by invitation or enterprise agreement.
Before you install
The API key is a secret and should not be committed to version control. Searches consume API credits under a metered beta plan (100 searches per month for beta testers), while listing data sources is free. Product image URLs are sent to DeepRecall's service for matching.

Installation

In SourceWeft

  1. Open DeepRecall - Product Safety Intelligence in the dashboard and add it to a workspace.
  2. Connect X-API-Key credentials. They are stored privately and never shown on public pages.
  3. 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/io.github.adrida%2Fdeeprecall-mcp/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": {
    "deeprecall-product-safety-intelligence": {
      "type": "http",
      "url": "https://mcp.deeprecall.io/mcp",
      "headers": {
        "X-API-Key": "<YOUR_API_KEY>"
      }
    }
  }
}

README

DeepRecall MCP Server

[MCP] [License]

Product Safety Intelligence for AI Agents via the Model Context Protocol.

Search 120,000+ recalled products from CPSC, FDA, EU Safety Gate, UK OPSS, Health Canada, OECD, RappelConso, and ACCC.

Quick Start

Use Hosted Server (Recommended)

Add to your MCP client config:

json
{  "mcpServers": {    "deeprecall": {      "url": "https://mcp.deeprecall.io/mcp",      "headers": {        "X-API-Key": "dr_live_your_api_key_here"      }    }  }}

Works with: Cursor, Claude Desktop, Windsurf, and any MCP-compatible client.

Requires API key - Replace dr_live_your_api_key_here with your key. See API Access below.

Self-Host

bash
git clone https://github.com/adrida/deeprecall-mcpcd deeprecall-mcppip install -r requirements.txtDEEPRECALL_API_KEY=your_key python server.py --http

Tools

search_recalls

Search for recalled products by text and/or images.

"Search for baby cribs with drop-side rails""Find recalls matching this stroller image""Check if this toy has been recalled in the EU"

Parameters:

NameTypeRequiredDescription
content_descriptionstringNo*Product description
image_urlsstring[]No*Product image URLs (1-10)
filter_by_data_sourcesstring[]NoFilter by agency
top_kintNoResults (1-100, default: 10)

*At least one of content_description or image_urls required.

get_data_sources

List available regulatory agencies (free, no API key).

Data Sources

IDAgencyRegion
us_cpscUS Consumer Product Safety CommissionUSA
us_fdaUS Food and Drug AdministrationUSA
safety_gateEU Safety Gate (RAPEX)Europe
uk_opssUK Office for Product Safety & StandardsUK
canada_recallsHealth CanadaCanada
oecdOECD GlobalRecallsInternational
rappel_consoRappelConsoFrance
accc_recallsACCCAustralia

Configuration

VariableDefaultDescription
DEEPRECALL_API_KEY-API key for hosted API
DEEPRECALL_API_URLhttps://api.deeprecall.ioAPI endpoint
PORT8000HTTP server port
ALLOWED_HOSTSlocalhost,127.0.0.1Allowed host headers

Docker

bash
docker build -t deeprecall-mcp .docker run -p 8000:8000 -e DEEPRECALL_API_KEY=your_key deeprecall-mcp

UCP Integration

This MCP server is designed for Universal Commerce Protocol (UCP) integration, providing the product safety layer for agentic commerce.

Agent Intent → Product Discovery → DeepRecall Safety Check → Checkout Decision

See ucp/capability.json for the UCP capability definition.

API Access

Note: DeepRecall is currently in closed beta. API access is available to:

  • Beta testers (by invitation)
  • Enterprise clients

Contact us to join the beta program.

Pricing (Beta)

TierSearchesAccess
Beta Tester100/monthBy invitation
BusinessCustom limitsContact sales
EnterpriseUnlimitedDedicated support

API Key Format

API keys start with dr_live_ (production) or dr_test_ (sandbox).

dr_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

Getting Your Key

  1. Contact us to request access
  2. Once approved, receive your key via email
  3. Store securely (never commit to version control)

For enterprise inquiries: [email protected]

Links

License

Apache 2.0 - See LICENSE

Source: README.md at commit 01ec986

Tools

2

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 Cases: - Pre-purchase safety checks: Before buying, verify if similar products were recalled - Supplier vetting: Check if a supplier's products have safety issues - Marketplace compliance: Verify products against recall databases - Consumer protection: Identify potentially hazardous products Data Sources: - us_cpsc: US Consumer Product Safety Commission - us_fda: US Food and Drug Administration - safety_gate: EU Safety Gate (Europe) - uk_opss: UK Office for Product Safety & Standards - canada_recalls: Health Canada Recalls - oecd: OECD GlobalRecalls portal - rappel_conso: French Consumer Recalls - accc_recalls: Australian Competition and Consumer Commission Cost: 1 API credit per search Args: content_description: Text description of the product (e.g., "children's toy with small parts") image_urls: List of product image URLs for visual matching (1-10 images) filter_by_data_sources: Limit search to specific agencies (optional) top_k: Number of results (1-100, default: 10) model_name: Fusion model - fuse_max (recommended), fuse_flex, or fuse input_weights: Weights for [text, images], must sum to 1.0 api_key: Your DeepRecall API key (optional if provided via X-API-Key header) Returns: Search results with matched recalls, scores, and product details Example: search_recalls( content_description="baby crib with drop-side rails", top_k=5 )

Parameterstop_kapi_keyimage_urlsmodel_nameinput_weightscontent_descriptionfilter_by_data_sources

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

Takes no parameters.

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

100% 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
  • Documentation15 pts
  • License10 pts