deeprecall-mcp
Search 120,000+ recalled products from CPSC, FDA, EU Safety Gate, and other global agencies via MCP. Enables AI agents to check product safety by text or image.
README
DeepRecall MCP Server
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:
{
"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_herewith your key. See API Access below.
Self-Host
git clone https://github.com/adrida/deeprecall-mcp
cd deeprecall-mcp
pip install -r requirements.txt
DEEPRECALL_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:
| Name | Type | Required | Description |
|---|---|---|---|
content_description |
string | No* | Product description |
image_urls |
string[] | No* | Product image URLs (1-10) |
filter_by_data_sources |
string[] | No | Filter by agency |
top_k |
int | No | Results (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
| ID | Agency | Region |
|---|---|---|
us_cpsc |
US Consumer Product Safety Commission | USA |
us_fda |
US Food and Drug Administration | USA |
safety_gate |
EU Safety Gate (RAPEX) | Europe |
uk_opss |
UK Office for Product Safety & Standards | UK |
canada_recalls |
Health Canada | Canada |
oecd |
OECD GlobalRecalls | International |
rappel_conso |
RappelConso | France |
accc_recalls |
ACCC | Australia |
Configuration
| Variable | Default | Description |
|---|---|---|
DEEPRECALL_API_KEY |
- | API key for hosted API |
DEEPRECALL_API_URL |
https://api.deeprecall.io |
API endpoint |
PORT |
8000 |
HTTP server port |
ALLOWED_HOSTS |
localhost,127.0.0.1 |
Allowed host headers |
Docker
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)
| Tier | Searches | Access |
|---|---|---|
| Beta Tester | 100/month | By invitation |
| Business | Custom limits | Contact sales |
| Enterprise | Unlimited | Dedicated support |
API Key Format
API keys start with dr_live_ (production) or dr_test_ (sandbox).
dr_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
Getting Your Key
- Contact us to request access
- Once approved, receive your key via email
- Store securely (never commit to version control)
For enterprise inquiries: contact@deeprecall.io
Links
- Hosted MCP: https://mcp.deeprecall.io/mcp
- REST API: https://api.deeprecall.io
- Documentation: https://docs.deeprecall.io
- MCP Registry: registry.modelcontextprotocol.io
License
Apache 2.0 - See LICENSE
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。