Redfish MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| REDFISH_PORT | No | Default port for Redfish API (used when not specified per-host) | 443 |
| MCP_TRANSPORT | No | Transport method: stdio, sse, or streamable-http | stdio |
| REDFISH_HOSTS | Yes | JSON array of Redfish endpoint configurations | [{"address":"127.0.0.1"}] |
| REDFISH_PASSWORD | No | Default password for authentication | |
| REDFISH_USERNAME | No | Default username for authentication | |
| REDFISH_AUTH_METHOD | No | Authentication method: basic or session | session |
| MCP_REDFISH_LOG_LEVEL | No | Logging level: DEBUG, INFO, WARNING, ERROR, CRITICAL | INFO |
| REDFISH_SERVER_CA_CERT | No | Path to CA certificate for server verification | |
| REDFISH_DISCOVERY_ENABLED | No | Enable automatic endpoint discovery | false |
| REDFISH_DISCOVERY_INTERVAL | No | Discovery interval in seconds | 30 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_resource_dataA | Given a Redfish resource URL (e.g., 'https:///redfish/v1'), fetches and returns its data as JSON. To construct a valid Redfish resource URL as input, use the following url schema 'https:///redfish/v1/'. |
| list_serversB | List configured Redfish servers that can be managed. Returns: list: A list of configured Redfish servers that can be managed |
| list_discovered_serversA | List discovered Redfish server candidates for review. Returns: list: A list of discovered Redfish server candidates. These candidates are informational only and are not managed unless explicitly configured. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
get_resource_data is clearly distinct from the list tools. list_servers and list_discovered_servers have overlapping purposes, but their descriptions clearly distinguish configured managed servers from unmanaged discovered candidates.
All tool names follow a consistent verb_noun snake_case pattern: get_resource_data, list_servers, list_discovered_servers. The naming is predictable and easy to navigate.
Three tools is minimal but reasonable for a server focused on Redfish resource inspection and server inventory. It avoids bloat, though the surface could be expanded with more management operations.
The tool set is effectively read-only, covering resource fetching and server listing, but lacks obvious Redfish management operations like configuring servers, powering systems, or performing updates. The generic get_resource_data helps but does not fill the action-level gaps.