Bricks MCP

Your AI Agents can now enable cloud infrastructure through our official MCP server in a simple and secure way

AI Companion for Cloud Infrastructure Workflow

Transform infrastructure management through conversational AI. Request infrastructure changes in natural language, review detailed deployment plans, and approve changes with full transparency.

Request: "Create a PostgreSQL database with Redis cache for staging"

Plan: Review complete AWS resource specifications, networking, and security configurations - Get a complete analysis on cost, operational and security risks. Deploy: Approve the plan to execute infrastructure changes

Getting Started

VS Code

Manually Install the MCP extension for VS Code:

1. Open VS Code Extensions (Ctrl+Shift+X or Cmd+Shift+X)

2. Search for "Model Context Protocol"

3. Install the MCP extension

4. Open Command Palette (Ctrl+Shift+P or Cmd+Shift+P)

5. Run "MCP: Add Server"

6. Configure server:

   • Name: bricks

   • Command: bricks

   • Args: ["mcp"]

Claude Desktop

Add the Bricks MCP server to your Claude Desktop configuration:

{
  "mcpServers": {
    "bricks": {
      "command": "bricks",
      "args": ["mcp"]
    }
  }
}

Configuration file location:

• ~/.claude/settings.json

Cursor

Enable MCP support in Cursor settings:

1. Open Cursor Settings (Cmd+, or Ctrl+,)

2. Navigate to Extensions → MCP

3. Add new server configuration:

   • Name: bricks

   • Command: bricks

   • Args: ["mcp"]

Windsurf

Configure MCP in your Windsurf workspace:

{
  "mcp": {
    "servers": {
      "bricks": {
        "command": "bricks",
        "args": ["mcp"],
        "env": {}
      }
    }
  }
}

Add this configuration to your .windsurf/settings.json file.

Other MCP Clients

For any MCP-compatible client, configure with:

• Command: bricks

• Arguments: ["mcp"]

• Protocol: STDIO

Consult your client's documentation for specific configuration steps.

Authentication

Authenticate using your existing Bricks CLI credentials:

bricks login

Example Operations

Infrastructure Planning

• "Plan a development s3 buckets matching the one on production"

• "Design a scalable database cluster with automated backups"

Deployment Management

• "Approve my latest staging deployment"

• "Show me the status of my recent AWS deployments"

• "List all pending deployments that needs my approval"

Resource Discovery

• "What blueprints are available for GCP workloads?"

• "Show me all environments and their current status"

• "Find database blueprints with high availability configuration"

Available tools

bricks-list-blueprints - Discover and search infrastructure templates bricks-list-environments - View environments and deployment context bricks-list-deployments - Query deployments with filtering options bricks-install - Deploy blueprints to target environments bricks-deployment-approve - Approve pending infrastructure changes bricks-deployment-status - Monitor deployment progress and status

---

Bricks MCP support is available in the latest Bricks CLI release (v1.54.1). Upgrade to access AI-driven infrastructure management capabilities.