A comprehensive middleware service and MCP server for accessing Israeli emergency alerts from the official Pikud Haoref (Israeli Home Front Command)
If you already use Pikud A Horef MCP, the pikud a horef mcp mcp server is the piece that lets your assistant work with it directly. A comprehensive middleware service and MCP server for accessing Israeli emergency alerts from the official Pikud Haoref (Israeli Home Front Command) API.
This project provides two ways to access Israeli emergency alert data using a publish-subscribe architecture:
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
Single — source polling** of emergency alerts (eliminates duplicate API calls)Real — time SSE streaming** via public webhook endpointevent — new_alert - When a new alert is detectedEndpoint — DescriptionTesting — The Testing tool exposed by this serverDependencies — The Dependencies tool exposed by this serverSetup — The Setup tool exposed by this serverLogs — Both services provide detailed logging. Check logs for: - API polling status - SSE client connections and authentication - MCP server webhookInstallation goes through your MCP client rather than a global install: point it at fuzzywuzzy on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
Configuration is passed through the environment: GEOIP_DB_PATH, DATABASE_PATH. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Among the monitoring and observability options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Pikud A Horef MCP's toolset — Single, Real, event and 5 more — is a fair guide to whether it matches your workflow. It is maintained by LeonMelamud; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| Single | source polling** of emergency alerts (eliminates duplicate API calls) |
| Real | time SSE streaming** via public webhook endpoint |
| event | new_alert - When a new alert is detected |
| Endpoint | Description |
| Testing | The Testing tool exposed by this server. |
| Dependencies | The Dependencies tool exposed by this server. |
| Setup | The Setup tool exposed by this server. |
| Logs | Both services provide detailed logging. Check logs for: - API polling status - SSE client connections and authentication - MCP server webhook connection status - Error messages - Security events |
{
"mcpServers": {
"pikud-a-horef": {
"command": "uvx",
"args": ["fuzzywuzzy"],
"env": {
"GEOIP_DB_PATH": "your-value",
"DATABASE_PATH": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| GEOIP_DB_PATH | Filesystem location the server is allowed to use. | Optional |
| DATABASE_PATH | Filesystem location the server is allowed to use. | Optional |
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Dashboards, Prometheus and Loki queries, incidents and alerts — observability by conversation.
Errors with full context — stack traces, issue triage and AI-powered root-cause analysis from Sentry's server.
Enables enhanced web research capabilities for large language models through intelligent search queuing and advanced content extraction.
Automates browser interactions and enables Large Language Models (LLMs) to interact with web pages through Playwright and Chrome DevTools Protocol
Guides tool usage by providing recommendations for MCP tools at each problem-solving stage.