ICE Locator MCP Server
Enables searching for ICE detainee locations using AI-powered natural language queries, with support for bulk operations, multilingual searches, and legal report generation for families and legal representatives.
README
ICE Locator MCP Server
A Model Context Protocol (MCP) server for searching ICE detainee locations with AI-powered natural language queries.
Features
- 🔍 Smart Search: Natural language queries with fuzzy matching
- 📊 Bulk Operations: Search multiple detainees simultaneously
- 🌐 Multilingual: Support for English, Spanish, and more
- 📋 Legal Reports: Generate comprehensive reports for legal use
- 🗺️ Heatmap Visualization: Interactive web app showing facility locations
Quick Start
Installation
pip install ice-locator-mcp
Claude Desktop Configuration
Add to your Claude Desktop config:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"ice-locator": {
"command": "ice-locator-mcp",
"args": []
}
}
}
Available Tools
🔍 Search Tools
| Tool | Description | Parameters |
|---|---|---|
search_detainee_by_name |
Search by personal information with fuzzy matching | first_name, last_name, date_of_birth, country_of_birth, middle_name, language, fuzzy_search |
search_detainee_by_alien_number |
Search by alien registration number (A-number) | alien_number, language |
smart_detainee_search |
AI-powered natural language search | query, context, suggest_corrections, language |
bulk_search_detainees |
Search multiple detainees simultaneously | search_requests, max_concurrent, continue_on_error |
generate_search_report |
Generate comprehensive reports for legal use | search_criteria, results, report_type, format |
📋 Prompts
| Prompt | Description | Arguments |
|---|---|---|
detainee_search_guide |
Guide for searching ICE detainees with best practices | search_type, user_role |
legal_report_template |
Template for generating legal reports from search results | report_type, client_name |
family_support_guide |
Comprehensive guide for families searching for detained relatives | relationship, language |
📚 Resources
| Resource | Description | Type |
|---|---|---|
ice://facilities/database |
Comprehensive database of ICE detention facilities | JSON |
ice://search/history |
Track and manage previous search queries and results | JSON |
ice://legal/templates |
Templates for legal documents and correspondence | Markdown |
ice://support/resources |
Resources for families of detainees | Markdown |
ice://statistics/trends |
Historical data and trends about ICE detention | JSON |
Usage Examples
# Natural language search
result = await smart_detainee_search(
query="Find Maria Rodriguez from Guatemala born around 1985"
)
# Name-based search
result = await search_detainee_by_name(
first_name="John",
last_name="Doe",
date_of_birth="1990-01-15",
country_of_birth="Mexico"
)
# Bulk search
result = await bulk_search_detainees(
search_requests=[...],
max_concurrent=3
)
Web App
View the interactive heatmap: ice-locator-mcp.vercel.app
Use Cases
- Legal Representatives: Locate clients in ICE custody
- Family Members: Find detained relatives with AI assistance
- Advocacy Organizations: Streamline detainee location workflows
- AI Assistants: Enable immigration-related support capabilities
Privacy & Security
- No Data Storage: Search data is not permanently stored
- Local Processing: All processing happens locally
- Optional Analytics: Privacy-first analytics with automatic data redaction
- Rate Limiting: Respectful usage with built-in rate limiting
License
MIT License - see LICENSE for details.
Support
- Issues: GitHub Issues
- Documentation: Full Documentation
⚠️ Important: This is an independent project not affiliated with ICE. Use responsibly and in compliance with applicable laws.
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。