Redfish

High-performance Go MCP Server providing Redfish API access for AI assistants and clients.

GitHub Stars

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "theoriginalaiexplorer-mcp-redfish-go": {
      "command": "./bin/redfish-mcp",
      "args": [],
      "env": {
        "REDFISH_PORT": "443",
        "MCP_TRANSPORT": "stdio",
        "REDFISH_HOSTS": "[{\"address\": \"192.168.1.100\", \"username\": \"admin\", \"password\": \"secret\"}]",
        "REDFISH_PASSWORD": "<REDFISH_PASSWORD>",
        "REDFISH_USERNAME": "<REDFISH_USERNAME>",
        "REDFISH_AUTH_METHOD": "session",
        "REDFISH_SERVER_CA_CERT": "<REDFISH_SERVER_CA_CERT>",
        "REDFISH_INSECURE_SKIP_VERIFY": "false"
      }
    }
  }
}

You can run a Go-based MCP Server that exposes Redfish resources to AI agents and applications. It provides high-performance, secure access to Redfish endpoints, supports multiple transports, and integrates with MCP clients for natural language workflows across data center infrastructure.

How to use

Install and run the Redfish MCP Server to enable AI-driven interactions with Redfish-enabled infrastructure. Start the server, configure the target Redfish hosts, and choose a transport to communicate with MCP clients. You will be able to discover configured Redfish servers and fetch resource data through MCP tools that expose Redfish endpoints in a structured, JSON-based format.

How to install

Prerequisites include Go 1.21 or later and access to Redfish-enabled infrastructure. After meeting prerequisites, you build the server, set up hosts, and run the binary.

# Build the server
go build -o bin/redfish-mcp ./cmd/redfish-mcp

# Set configuration for Redfish hosts (example)
export REDFISH_HOSTS='[{"address": "192.168.1.100", "username": "admin", "password": "secret"}]'

# Run the server with the default stdio transport
./bin/redfish-mcp

Configuration and provisioning

Configuration can be supplied via environment variables or a JSON config file. The following environment variables are used to configure hosts, transport, and security.

# Environment variables example
export REDFISH_HOSTS='[{"address": "192.168.1.100", "port": 443, "username": "admin", "password": "secret123", "auth_method": "session"}]'
export MCP_TRANSPORT="stdio"   # default transport
export REDFISH_INSECURE_SKIP_VERIFY=false
export REDFISH_LOG_LEVEL="INFO"

Security and TLS considerations

The server supports SSL/TLS for Redfish authentication and data transport. You can opt into insecure skip-verify for development or testing with self-signed certificates, but you should not enable this in production. Use proper CA certificates and configure TLS options to protect your infrastructure.

export REDFISH_INSECURE_SKIP_VERIFY=true

Tools and usage patterns

Two primary MCP tools are exposed to interact with Redfish infrastructure: one to list configured servers and another to fetch resource data from a Redfish endpoint.

# List all configured Redfish servers
# (This is a conceptual usage example; actual tool invocation is via MCP client integration)

Available tools

list_servers

Lists all configured Redfish servers that can be accessed.

get_resource_data

Fetches data from a specific Redfish resource endpoint.

Built by

VeilStrat

AI signals for GTM teams