Skip to main content
Glama

raidcom-mcp: build Hitachi raidcom commands from plain-language requests

npm Release CI

Hitachi raidcom command builder (Community) MCP server

A community MCP server that turns a request such as "present four 100 GB volumes from pool 0 to host esx01 on CL1-A and CL2-A" into validated raidcom commands. It is build-only: it never connects to a storage system, never runs a command and holds no credentials. It returns command text (or a shell script) for a person to review and run on a host with CCI installed. That makes it safe to host online for anyone to use.

It is an independent project, not an official Hitachi Vantara product.

What it does

  • Finds the right command. raidcom_list_commands ranks the 178 commands in the catalogue against a question (BM25 with synonyms and verb intent) and says how confident it is.

  • Builds one command. raidcom_build_command takes a command name and options as structured data, checks them against the manual's syntax and the storage model's limits, and returns the command line.

  • Builds many. raidcom_build_script repeats steps over ranges (foreach, zip), adds get command_status after asynchronous commands, optionally locks the resource group, and returns a script that stops at the first failure.

  • Ready-made workflows. raidcom_list_recipes and raidcom_build_recipe cover 14 common jobs: FC, iSCSI and NVMe/TCP provisioning, DP pools, mainframe (3390) pools, extending and deleting volumes, command devices, zero-page reclaim, inventory, copy groups.

  • Checks an existing command. raidcom_check_command parses a pasted command line (never executing it; shell operators are refused) and reports every problem.

  • Knows the model limits. raidcom_model_limits gives the LDEV, LUN, pool, serial and port ranges of VSP One Block 24/26/28, VSP 5000 series and VSP E series.

All eight tools are marked read-only. There is no tool that executes anything.

Related MCP server: Komodo MCP Server

Use the hosted server

A public instance runs at https://raidcom-mcp.onrender.com/mcp. It needs no sign-in.

  • Claude (desktop or web): Settings → Connectors → Add custom connector, paste the URL, leave the advanced (OAuth) settings empty.

  • Claude Code: claude mcp add --transport http raidcom https://raidcom-mcp.onrender.com/mcp

  • Microsoft 365 Copilot (Copilot Studio): your agent → Tools → Add a tool → New tool → Model Context Protocol; paste the URL, authentication None.

  • GitHub Copilot (VS Code): add { "servers": { "raidcom": { "type": "http", "url": "https://raidcom-mcp.onrender.com/mcp" } } } to .vscode/mcp.json, then use Copilot Chat in Agent mode.

To run it yourself instead, see Setup.

How the catalogue is made

spec/raidcom-catalog.json is generated by scripts/generate-catalog.mjs from the text of the Command Control Interface Command Reference (MK-90RD7009). For every command it keeps the name, supported models, a one-line summary, each syntax form (as a small grammar), each option's value shape and a short description, and the command lines of the manual's examples. Hitachi's prose, tables and output samples are not copied. The manuals themselves are not part of this repository; to regenerate the catalogue with your own copy:

pdftotext -layout CCI_Command_Reference.pdf cci-reference.txt
npm run generate-catalog -- cci-reference.txt

tests/unit/catalog.test.mjs replays every example in the manual through the parser and validator (about 96% pass; the rest are places where the manual's syntax line and its examples disagree).

Validation

  • Unknown options, wrong number of values, values outside an option's allowed words, and missing required options (checked against the syntax grammar) are errors with a suggested fix.

  • LDEV IDs, LUN IDs, pool IDs, serial numbers and port names (CL1-A, CL3-B-12) are checked against the model you give, or the widest range of any model.

  • Values that a shell could misread (; | & $ \ > < ' "and so on) are refused, values containing spaces or#are quoted, and values starting with- are refused so they can't add options. Global options (instance, pair_type, serial`, ...) are checked before anything is written. See SECURITY.md.

  • LDEV IDs can be decimal, 0x hex or mainframe CU:LDEV (dd:0f); recipes and scripts expand ranges such as 100-109 and dd:00-dd:0f.

  • Because the manual's syntax lines are occasionally incomplete, strict: false turns missing option errors into warnings. Unknown options and out-of-range values stay errors.

  • Out of scope: the pair* commands (paircreate, pairdisplay, ...) from the Quick Reference, and raidcom -login/-logout lines as commands of their own (scripts can add them with login: true, reading $RAIDCOM_USER and $RAIDCOM_PASSWORD from the shell).

Setup

You need Node.js 22.19 or later. The server is on npm, so most clients can start it with npx:

Claude Code

claude mcp add raidcom -- npx -y raidcom-mcp

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "raidcom": { "command": "npx", "args": ["-y", "raidcom-mcp"] }
  }
}

From source

git clone https://github.com/visubramaniam/raidcom-mcp.git
cd raidcom-mcp
npm ci
npm run build

Then use node /path/to/raidcom-mcp/dist/index.js as the command in the examples above.

Claude Desktop, standalone packages

Each release has a Claude Desktop extension (.mcpb), standalone packages for macOS, Linux and Windows with Node.js bundled, the npm package, and a skill zip. See INSTALL.md.

Claude Code plugin

/plugin install raidcom-community --marketplace visubramaniam/raidcom-mcp

See README.plugin.md.

Hosted over HTTP

RAIDCOM_TRANSPORT=http RAIDCOM_HTTP_HOST=0.0.0.0 RAIDCOM_HTTP_TOKEN=$(openssl rand -hex 32) \
RAIDCOM_HTTP_BEHIND_TLS_PROXY=true RAIDCOM_HTTP_ALLOWED_HOSTS=raidcom.example.com node dist/index.js

The endpoint is /mcp (stateless Streamable HTTP). /healthz reports the version and, behind a proxy, the address the server takes as the caller's, to check the proxy settings.

Clients that add servers as connectors (Claude, Microsoft 365 Copilot) can't send a fixed bearer token: they connect without authentication or through OAuth, which this server doesn't implement. For them, run without a token and with RAIDCOM_HTTP_OPEN=true, as the public instance does. Behind Cloudflare (Render, for example), set RAIDCOM_HTTP_CLIENT_IP_HEADER=cf-connecting-ip so the rate limits apply per user. See INSTALL.md and README.docker.md.

Configuration

Variable

Default

Meaning

RAIDCOM_TRANSPORT

stdio

stdio or http

RAIDCOM_HTTP_HOST

127.0.0.1

Address to listen on

RAIDCOM_HTTP_PORT

8361

Port (0 picks a free one)

RAIDCOM_HTTP_TOKEN

none

Bearer token, at least 32 characters. Required unless RAIDCOM_HTTP_OPEN=true

RAIDCOM_HTTP_OPEN

false

Serve anyone who can reach the port, without a token

RAIDCOM_HTTP_TLS_CERT, RAIDCOM_HTTP_TLS_KEY

none

PEM files; the server then speaks HTTPS

RAIDCOM_HTTP_BEHIND_TLS_PROXY

false

A proxy or load balancer ends TLS. Needed for non-loopback addresses without TLS

RAIDCOM_HTTP_ALLOWED_HOSTS

none

Extra Host values to accept (* for any)

RAIDCOM_HTTP_ALLOWED_ORIGINS

none

Origin values to accept (* for any)

RAIDCOM_HTTP_RATE_LIMIT

120

Requests per minute per client (0 for none)

RAIDCOM_HTTP_CLIENT_IP_HEADER

none

A header your proxy sets to the client's address, e.g. cf-connecting-ip behind Cloudflare (Render uses Cloudflare). Takes precedence over X-Forwarded-For

RAIDCOM_HTTP_DEBUG_CLIENT

true

/healthz also shows the forwarding headers it received (the caller's own request), to choose the two settings above. Set to false to turn it off

RAIDCOM_HTTP_TRUST_PROXY

false

Take the client address from X-Forwarded-For: true for one proxy in front, or the number of proxies (see INSTALL.md)

MCPRUSH_TOKEN

none

Token issued by the mcprush marketplace. Adds a second endpoint (below) that answers only requests carrying it in x-mcprush-token; /mcp is unchanged

RAIDCOM_HTTP_MCPRUSH_PATH

/mcprush

Path of that endpoint

RAIDCOM_CATALOG, RAIDCOM_LIMITS, RAIDCOM_RECIPES, RAIDCOM_EXAMPLES

bundled

Use another spec file (an empty RAIDCOM_EXAMPLES turns the example questions off)

Values are trimmed, and true/false settings accept any case; any other value for them stops the server with a message. At startup the server warns about RAIDCOM_ variables it doesn't recognise (a misspelt name, or one with a stray space), and over HTTP logs one line with its effective settings.

Tests

npm test

runs the unit tests (tests/unit) and the search evaluation (tests/search-eval.mjs: 40 tuning and 30 held-out requests, each with a minimum top-1 and top-3 score that may only go up, and a check that results rated high-confidence are right at least 85% of the time). npm run package builds the release packages and npm run smoke tests the npm package as installed.

Documentation

The wiki has a quick start, deployment guide, tools and recipe reference, troubleshooting and more.

Contributing

See CONTRIBUTING.md. Security problems: SECURITY.md. Privacy: PRIVACY.md.

License

MIT, see LICENSE. "Hitachi", "raidcom" and "VSP" are trademarks of their owners; this project is not affiliated with or endorsed by Hitachi.

Available Tools

8 tools
raidcom_build_commandBuild a raidcom commandA
Read-onlyIdempotent

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 add ldev -pool 0 -ldev_id 256 -capacity 100G -I0. For many similar commands use raidcom_build_script, not repeated calls. When the user asks for a command, show them the command from the result.

Inputs: command (required), model, global, strict, +1 more.

raidcom_build_recipeBuild a raidcom recipe scriptA
Read-onlyIdempotent

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.

Inputs: params (required), recipe (required), login, model, +3 more.

raidcom_build_scriptBuild a raidcom scriptA
Read-onlyIdempotent

Build a shell script of raidcom commands from steps. Each step is a command with options, optionally repeated with foreach (every combination) or zip (values advance together), so "create LDEVs 100 to 109 in pool 0, then map each to port CL1-A" is two steps. Every expanded command is validated; the script is returned only if all of them are valid, otherwise you get the errors per step. The script checks each command's exit status, adds raidcom get command_status after asynchronous commands, and can lock the resource group and log in (credentials are read from RAIDCOM_USER and RAIDCOM_PASSWORD in the user's shell, never written into the script). Nothing is executed.

Inputs: steps (required), login, model, global, +3 more.

raidcom_check_commandCheck a raidcom command lineA
Read-onlyIdempotent

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.

Inputs: command_line (required), model, strict.

raidcom_describe_commandDescribe a raidcom commandA
Read-onlyIdempotent

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.

Inputs: command (required), option.

raidcom_list_commandsFind raidcom commandsA
Read-onlyIdempotent

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 query (plain words, e.g. "map a volume to a host group", "grow a pool", "show free ldev ids"), ranks matching commands and rates the confidence of the top result. With action and/or object, lists exactly those commands. Then call raidcom_describe_command, or raidcom_build_command if you already know the options.

Inputs: limit, query, action, object.

raidcom_list_recipesList raidcom recipesA
Read-onlyIdempotent

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 recipe, shows its parameters and steps. With query, ranks recipes by keyword. Use raidcom_build_recipe to turn one into a script.

Inputs: query, recipe.

raidcom_model_limitsShow storage model limitsA
Read-onlyIdempotent

Valid parameter ranges for a storage model (serial number, LDEV ID, pool ID, LU number, port names), taken from the Command Reference appendices. Without model, lists the models.

Inputs: model.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.1/5.0

    Scored across 8 tools

    Disambiguation4/5

    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.

    Naming Consistency4/5

    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.

    Tool Count5/5

    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.

    Completeness4/5

    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.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      C
      quality
      B
      maintenance
      Enables deploying and managing infrastructure via natural language, including project/domain management, compute nodes, image deployment, and CI/CD integration.
      70
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables managing OpenI platform resources (login, query nodes, submit jobs, view logs) via natural language in Claude or Codex, following a kubectl/docker-style CLI.
      150
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables building and configuring NiCE CXone tenant resources—skills, outbound dialer config, agents, teams, campaigns, DNC groups, calling lists, and Studio IVRs—from plain English via MCP, with diagramming and server-side validation. Read-only operations and safe writes are supported, while destructive actions and dialing ignition are deliberately blocked.
      5
      MIT