@supstack/cli
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@@supstack/cliresearch magnesium for sleep quality"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@supstack/cli
Evidence-based supplement intelligence in your terminal — and an MCP server for AI agents.
A thin client over the public SupStack API. Read-only, no account required. One capability registry powers both the CLI and the MCP server.
Status: Phase 2 (accounts) in progress. All read commands below work, plus an MCP server and
login/whoami. Install withnpm install -g @supstack/cli.
Install
# Homebrew (macOS / Linux)
brew install drbaher/supstack/supstack
# or npm
npm install -g @supstack/cli
# or run without installing
npx -y @supstack/cli define adaptogenThen enable shell completion: supstack completion install.
From source (in this directory): npm install && npm run build && node dist/index.js define adaptogen.
Related MCP server: MindOS
Usage
supstack research magnesium --protocol # full evidence summary for one supplement
supstack search --goal deep-sleep -n 5 # search by name or filter
supstack compare magnesium glycine # 2–3 head-to-head
supstack studies "sleep" --type rct # research library
supstack interactions caffeine l-theanine --pathway # interaction check (deep pair analysis)
supstack interactions magnesium potassium --medication lisinopril # supplement × drug check
supstack stack add magnesium --dose 400mg --timing bedtime # local stack (+ dose/timing/brand)
supstack stack sync # sync local ⇄ your account (login required)
supstack goals --category sleep # list goal ids (for rate/recommend)
supstack rate --goals deep-sleep,sharpen-focus # grade your stack A–F by goal coverage
supstack experiments start magnesium deep-sleep # run an N-of-1 experiment (requires login)
supstack export --format md # export your stack
supstack define bioavailability # glossary lookup
supstack <command> --json # machine-readable output on any command
supstack --helpAccount (Phase 2)
supstack login # sign in via device-code flow (opens the browser to confirm)
supstack whoami # show the signed-in account
supstack logout # sign out and revoke this device's tokenlogin shows a one-time code, opens https://supstack.me/activate, and finishes
once you approve in the browser. The token lives in ~/.supstack/config.json
(0600). Reads work fully anonymously — an account unlocks personalized features.
Once logged in, sync your stack with your account:
supstack stack pull # local ← your account
supstack stack push # local → your account (keeps dosage/timing/brand for kept items)
supstack stack sync # additive merge of both; preserves existing cloud metadata
supstack profile # view your health profile
supstack profile set --age 35 --sex male --weight 80 --weight-unit kg
supstack recommend # personalized picks from your goals + stack
supstack experiments list # your N-of-1 experiments + verdicts
supstack track log # log today's stack as taken
supstack track adherence # your adherence rate, streak, per-supplementAs an MCP server
supstack mcp # stdio MCP server exposing all capabilities as toolsThis gives an agent the full SupStack toolset. Read-only (no account needed):
supstack_research, supstack_search, supstack_compare, supstack_studies,
supstack_interactions, supstack_stack, supstack_rate_stack, supstack_export,
supstack_define.
Account-scoped tools are also exposed — supstack_recommend,
supstack_profile_get / supstack_profile_set, supstack_experiments_list /
supstack_experiments_get, supstack_track_log, supstack_track_adherence
(plus cloud supstack_stack pull/push/sync). These require the user to be signed
in (supstack login, or a SUPSTACK_TOKEN); without a token they return a clear
"not logged in" error rather than failing. Mutating tools (profile_set,
track_log) are flagged readOnlyHint: false for the agent.
Claude Code (one command):
claude mcp add supstack -- supstack mcpClaude Desktop — add to claude_desktop_config.json
(macOS: ~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"supstack": {
"command": "supstack",
"args": ["mcp"]
}
}
}Or run it without a global install via
"command": "npx", "args": ["-y", "@supstack/cli", "mcp"]. To use a local checkout, point at the built entrypoint —"command": "node", "args": ["/absolute/path/to/supstack-cli/dist/index.js", "mcp"](runnpm run buildfirst).
Configuration
Env var | Default | Purpose |
|
| API base URL (override for local dev) |
| — | Optional API key (anonymous works at 60/min/IP) |
|
| Response cache TTL in seconds |
| — | Set to disable the response cache |
|
| Per-request timeout in seconds (or use |
|
| Directory for config, stack, and cache |
| — | Override the stored account token (from |
| — | Disable auto-minting of the anonymous instant-token |
| — | Disable the "update available" notice (also honours |
| — | Disable ANSI colour |
| — | Force ANSI colour on (even when piped) |
Global flags available on any command: --json, --no-cache, --timeout <seconds>, --color / --no-color, -q, --quiet.
supstack auth set-key <key> persists a key to ~/.supstack/config.json (written 0600).
Response cache
Read-only API responses are cached under ~/.supstack/cache/ (1-hour TTL by
default) to keep repeat lookups well under the 60/min rate limit. Bypass it per
command with --no-cache, or manage it with supstack cache clear /
supstack cache path. The cache is bounded (oldest entries pruned past a cap).
Shell completion
One-step install for your current shell (writes the script and wires your rc file
idempotently; uninstall reverses it):
supstack completion install # detects bash | zsh | fish from $SHELL…or generate the script yourself:
supstack completion bash >> ~/.bashrc
supstack completion zsh > "${fpath[1]}/_supstack"
supstack completion fish > ~/.config/fish/completions/supstack.fishCompletions are dynamic — the script forwards what you've typed to
supstack __complete, which offers the right thing for the position:
top-level commands and sub-actions (
stack <TAB>→add remove list pull push sync)supplement slugs where a slug is expected (
research <TAB>,compare a <TAB>,stack add <TAB>,track log <TAB>)goal ids after
search --goal <TAB>
Slug/goal lists are fetched once from the API and cached under
~/.supstack/completion/ (24-hour TTL). Pre-warm or refresh them with:
supstack completion refreshExit codes
Commands exit with a semantic code so scripts and MCP wrappers can branch on the kind of failure:
Code | Meaning |
| Success |
| Generic error (incl. 5xx) |
| Auth required/rejected (not logged in, 401, 403) |
| Not found (404) |
| Rate limited (429) |
| Network failure / timeout |
| Invalid input (bad/missing args or flags, unknown command, schema validation, 400/422) |
Develop
npm test # unit tests (mocked fetch)
npm run type-check # tsc --noEmit
npm run build # tsup → dist/See CLAUDE.md for the capability pattern and how to add a command.
License
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAquality-maintenanceSupplement safety MCP server for AI agents. FDA FAERS signals, CYP450 pathways, 584 compound aliases. Works with Claude Desktop, LangChain, CrewAI.Last updated51
- Alicense-qualityAmaintenanceLocal-first knowledge base MCP server. Lets AI agents (Claude Code, Cursor, etc.) read and write your personal knowledge base through 20 MCP tools. Zero cloud dependency — all files stay on your machine.Last updated1,758656MIT
- AlicenseAqualityBmaintenanceA local-first MCP server that gives AI coding agents persistent memory and controlled commands. Features a git-backed markdown knowledge vault with FTS5 search, surgical section edits, token-aware context budgeting, and a sandboxed command engine with human approval gates. Works with Claude Code, Cursor, Copilot, Gemini, and more.Last updated531Apache 2.0
- Alicense-qualityBmaintenanceEvidence-based supplement recommendation MCP server covering 17 supplements and 40+ conditions with medication interaction checking and form quality classification.Last updated93MIT
Related MCP Connectors
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
An MCP server that gives your AI access to the source code and docs of all public github repos
Person-owned, portable AI memory as a remote MCP server, readable and writable by any MCP client.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/DrBaher/supstack-cli'
If you have feedback or need assistance with the MCP directory API, please join our Discord server