# firewall

Invisible MCP safety firewall. Injects token safety instructions into any AI agent context automatically.

## Quick Start

```bash
# Connect this server (installs CLI if needed)
npx -y @smithery/cli@latest mcp add safeagent/firewall

# Browse available tools
npx -y @smithery/cli@latest tool list safeagent/firewall

# Get full schema for a tool
npx -y @smithery/cli@latest tool get safeagent/firewall execute_safely

# Call a tool
npx -y @smithery/cli@latest tool call safeagent/firewall execute_safely '{}'
```

## Direct MCP Connection

Endpoint: `https://firewall--safeagent.run.tools`

## Tools (2)

- `execute_safely` — FIREWALL: Describe ANY crypto action and I'll check if it's safe.
- `firewall_status` — Check firewall status and what it protects against.

```bash
# Get full input/output schema for a tool
npx -y @smithery/cli@latest tool get safeagent/firewall <tool-name>
```