What dependencies are required to run the server?
Python 3.8+ and a Check Point Management Server with API access are required. Dependencies are listed in `requirements.txt`.
@ngardiner
Basic information
Anthropic MCP servers to enable AI agent integration and autonomous defense for Check Point firewalls, endpoint, and more.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"checkpoint-security-mcp-servers": {
"command": "python",
"args": [
"-m",
"venv",
"venv"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
checkpoint-security-mcp-servers is an open-source implementation of Anthropic’s Model Context Protocol (MCP) servers designed for Check Point security products. It enables AI agents to interact with Check Point firewalls, endpoint solutions, and logging capabilities through a standardized protocol. This is an independent community project, not officially affiliated with Check Point Software Technologies.
Clone the repository, set up a Python 3.8+ virtual environment, install dependencies from requirements.txt, configure a Check Point Management API key and manager URL, then run the desired server (e.g., python src/firewall/server.py). Connect an MCP-compatible AI client (like Claude Desktop) over standard I/O to discover and invoke tools such as checkpoint_login_test.
Python 3.8+ and a Check Point Management Server with API access are required. Dependencies are listed in `requirements.txt`.
Obtain an API key from your Check Point Management Server and note the manager URL (IP/hostname and port). For initial testing with self-signed certificates you may use `verify=False`, but production environments require proper certificate validation.
Only the `checkpoint_login_test` Tool in the Firewall MCP server, which tests connectivity to the Management API using an API key.
Full firewall tools (e.g., `BlockIPTool`), log retrieval resources, Harmony Endpoint server with endpoint isolation and status checks, and improved error handling.
The server runs over standard I/O (stdin/stdout) and waits for an MCP client connection. No HTTP or WebSocket transport is mentioned.

The BetterBugs MCP (Model Context Protocol) enables you to load BetterBugs bug reports (via report links) directly to your preferred AI Agents and developer environments with MCP Client capabilities (such as Cursor, VS C
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

Official Porkbun MCP server, maintained by Porkbun. Check domain availability and pricing, register, renew and transfer domains, and manage DNS records, nameservers, URL forwarding, glue records, DNSSEC and domain contac

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools
Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.
Comments