Raidcom MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RAIDCOM_LIMITS | No | Use another model-limits spec file. | bundled |
| RAIDCOM_CATALOG | No | Use another catalogue spec file. | bundled |
| RAIDCOM_RECIPES | No | Use another recipes spec file. | bundled |
| RAIDCOM_EXAMPLES | No | Use another examples spec file; an empty value turns the example questions off. | bundled |
| RAIDCOM_HTTP_HOST | No | Address to listen on when using HTTP transport. | 127.0.0.1 |
| RAIDCOM_HTTP_OPEN | No | Serve anyone who can reach the port, without a token. | false |
| RAIDCOM_HTTP_PORT | No | Port to listen on when using HTTP transport (`0` picks a free one). | 8361 |
| RAIDCOM_TRANSPORT | No | Transport for the MCP server: `stdio` or `http`. | stdio |
| RAIDCOM_HTTP_TOKEN | No | Bearer token, at least 32 characters. Required unless `RAIDCOM_HTTP_OPEN=true`. | none |
| RAIDCOM_HTTP_TLS_KEY | No | PEM key file; when set with `RAIDCOM_HTTP_TLS_CERT`, the server speaks HTTPS. | none |
| RAIDCOM_HTTP_TLS_CERT | No | PEM certificate file; when set with `RAIDCOM_HTTP_TLS_KEY`, the server speaks HTTPS. | none |
| RAIDCOM_HTTP_RATE_LIMIT | No | Requests per minute per client (`0` for none). | 120 |
| RAIDCOM_HTTP_TRUST_PROXY | No | Take the client address from `X-Forwarded-For`. | false |
| RAIDCOM_HTTP_ALLOWED_HOSTS | No | Extra `Host` values to accept (`*` for any). | none |
| RAIDCOM_HTTP_ALLOWED_ORIGINS | No | `Origin` values to accept (`*` for any). | none |
| RAIDCOM_HTTP_BEHIND_TLS_PROXY | No | A proxy or load balancer ends TLS. Needed for non-loopback addresses without TLS. | false |
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 | {} |
| prompts | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| raidcom_list_commandsA | Find raidcom commands. Use this first when you do not know the exact command name. With no arguments, lists every object (ldev, lun, host_grp, pool, ...) with the actions available on it. With |
| raidcom_describe_commandA | Everything needed to build one raidcom command: what it does, which models support it, whether it is read-only, destructive or asynchronous, each syntax form, every option with the number and kind of values it takes (and the words it accepts, where it accepts only a few), and examples. Call it before raidcom_build_command when you are unsure which options a command needs or which of its syntax forms fits the request. |
| raidcom_build_commandA | Build one raidcom command from structured arguments and validate it. Nothing is executed and no storage system is contacted: you get command text to review and run elsewhere. Unknown options, wrong value counts, missing required options, bad port names and out-of-range LDEV, LUN, pool and serial numbers are reported as errors with a fix. Example: {"command": "add ldev", "options": {"-pool": 0, "-ldev_id": 256, "-capacity": "100G"}, "model": "vsp-one-b28", "global": {"instance": 0}} → |
| raidcom_check_commandA | Validate and explain a raidcom command line the user already has (for example one pasted from a runbook). It is parsed, not executed: shell operators such as ; | & > are refused. Returns the normalised command, what each option means, and every problem found. Credentials after -login are dropped. |
| raidcom_build_scriptA | Build a shell script of raidcom commands from steps. Each step is a command with options, optionally repeated with |
| raidcom_list_recipesA | Ready-made workflows: provision volumes to an FC, iSCSI or NVMe/TCP host, create or grow a pool, create a mainframe (3390) pool, extend or delete volumes, create a command device, reclaim zero pages, read-only inventory, copy groups. With no arguments lists them. With |
| raidcom_build_recipeA | Build the script for a recipe from its parameters (see raidcom_list_recipes). Lists such as ldev_ids accept ranges: ["100-109"]. Example: recipe provision-fc-volumes with {"pool": 0, "ldev_ids": ["100-103"], "capacity": "100G", "ports": ["CL1-A", "CL2-A"], "host_grp": "esx01", "host_mode": "VMWARE_EX", "wwns": ["210000e08b0256f8"]}. Returns the script and the individual commands. Nothing is executed. |
| raidcom_model_limitsA | Valid parameter ranges for a storage model (serial number, LDEV ID, pool ID, LU number, port names), taken from the Command Reference appendices. Without |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| build-raidcom-commands | Turn a storage task into validated raidcom commands. |
| explain-raidcom-command | Explain and check an existing raidcom command line. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| raidcom conventions | Login, instances, serial numbers, asynchronous commands, resource locking. |
| Minimal HORCM configuration | What the host that runs raidcom needs. |
| Command list | Every raidcom command in the catalogue with its one-line summary. |
TDQS
Scored across 8 tools
The three "build" tools (build_command, build_script, build_recipe) share a surface but are clearly delineated by scope: one command, many commands, or a prebuilt workflow, and the descriptions explicitly cross-reference each other. Discovery (list_commands), documentation (describe_command), and validation (check_command) each have distinct roles, leaving only mild build_script-vs-build_recipe overlap.
All eight tools use a uniform raidcom_ prefix, snake_case, and verb-first style (build_, list_, describe_, check_). The only deviation is raidcom_model_limits, which is noun-based rather than verb_noun, but it remains readable and unambiguous.
Eight tools is a well-scoped set for an offline raidcom command builder, and each tool earns its place: discovery, docs, single build, multi-step build, recipe listing, recipe build, validation, and model limits. No obvious padding or redundancy.
The lifecycle is well covered from discovery through description, validation, single-command build, multi-step scripts, and recipes, with no execution by design. Minor gaps remain, such as a tool to interpret raidcom error codes or the asynchronous command_status output the generated scripts rely on.