# Golem Security

> Golem Security is a free MCP server for security. Threat-intelligence verdicts on a URL, domain or IP before a coding agent connects. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Free
- **Platforms:** API, Web
- **Website:** https://golem.team
- **MCP Registry name:** team.golem/security
- **Categories:** security
- **Listing updated:** 2026-11-16

## About

Golem Security is the remote MCP endpoint of Golem, a product that sits in the path of coding-agent activity. It gives an agent a threat-intelligence verdict on a URL, domain or IP address before the agent touches it, so a poisoned link in a web page or pull-request comment can be caught at the moment of use.

The endpoint is a streamable-HTTP server hosted by Golem. Golem's wider platform describes local rule checks that take microseconds, optional kernel sandboxing of shell commands for Claude Code, and signed, hash-chained records of agent actions. The site says the platform works with clients such as Claude Code, Cursor, Codex, GitHub Copilot and Gemini CLI.

It suits security-minded teams that let coding agents read untrusted content and want a check on the network destinations those agents reach.

## Features

- **Reputation verdicts:** Returns a threat-intelligence verdict for a URL, domain or IP address.
- **Remote MCP endpoint:** Connects over streamable HTTP, so no local install is needed to query it.
- **Part of Golem platform:** Works alongside Golem's rules, session tainting and approval holds for agent tool calls.
- **Signed audit trail:** Golem signs each recorded action with ES256 and chains entries with SHA-256.
- **Wide client coverage:** The vendor lists Claude Code, Cursor, Codex, GitHub Copilot and Gemini CLI among supported agents.

## Good for

- Check a link from a PR comment before an agent fetches it
- Screen domains an agent wants to call during automated coding runs
- Add a reputation check to a coding-agent security setup
- Give auditors a verifiable record of what an agent was allowed to reach

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http security https://context.golem.team/security
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://context.golem.team/security
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "security": {
      "url": "https://context.golem.team/security"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "security": {
      "type": "http",
      "url": "https://context.golem.team/security"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "security": {
      "serverUrl": "https://context.golem.team/security"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "security": {
      "type": "http",
      "url": "https://context.golem.team/security"
    }
  }
}
```

## FAQ

### What does this server check?

It returns threat-intelligence verdicts on a URL, domain or IP before a coding agent connects to it.

### Is Golem free?

The site says Golem is free during its public preview, and it also offers free open-source tools.

### Which operating systems does Golem run on?

macOS, Linux and Windows; the VM sandbox needs Apple silicon with macOS 26 or later, or Linux with KVM.

### What happens if Golem stops?

The shell jail keeps a baseline, agent hooks let calls through, and MCP calls fail open by default unless a profile makes them fail closed.

### Is Golem Security free?

Yes. Golem Security is free to use.

### How do I add Golem Security to Claude Code?

Run this command in your terminal: claude mcp add --transport http security https://context.golem.team/security

### What are the best alternatives to Golem Security?

The closest alternatives to Golem Security are REA, Agent Roast, Midplane, Leash and Tinplate Edge AI Safety, Security & EU Compliance.

## Alternatives

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [Agent Roast](https://ai-powered.com/mcp/agent-roast): Agent Roast is an open-source MCP server for developer tools.
- [Midplane](https://ai-powered.com/mcp/midplane): Midplane is an open-source MCP server for databases.
- [Leash](https://ai-powered.com/mcp/leash): Leash is a free MCP server for security.
- [Tinplate Edge AI Safety, Security & EU Compliance](https://ai-powered.com/mcp/tinplate-edge-ai-safety-security-and-eu-compliance): Tinplate Edge AI Safety, Security & EU Compliance is a freemium MCP server for security.
- [SecureCloud](https://ai-powered.com/mcp/securecloud): SecureCloud is a free MCP server for security.
- [Eikino](https://ai-powered.com/mcp/eikino): Eikino is a freemium MCP server for security.
- [SynomosAI Governance MCP](https://ai-powered.com/mcp/synomosai-governance-mcp-2): SynomosAI Governance MCP is an open-source MCP server for security.

---
Source: https://ai-powered.com/mcp/golem-security
