Server data from the Official MCP Registry
creative-constraints — an original deck of 162 domain-neutral creative constraints, drawn by…
About
creative-constraints — an original deck of 162 domain-neutral creative constraints, drawn by…
Remote endpoints: streamable-http: https://gateway.pipeworx.io/creative-constraints/mcp
Security Report
Valid MCP server (1 strong, 1 medium validity signals). No known CVEs in dependencies. Package registry verified. Imported from the Official MCP Registry. Trust signals: trusted author (1983/1985 approved).
47 tools verified · Open access · 1 issue found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
Permissions Required
This plugin requests these system permissions. Most are normal for its category.
What You'll Need
Set these up before or after installing:
Environment variable: PIPEWORX_API_KEY
How to Install & Connect
Available as Local & Remote
This plugin can run on your machine or connect to a hosted endpoint. during install.
Documentation
View on GitHubFrom the project's GitHub README.
@pipeworx/creative-constraints
Draws from an original, 162-card deck of domain-neutral creative constraints — each card is one imperative sentence an agent or a team can apply to any task (a product launch, an essay, an onboarding flow, a dinner), plus one sentence on why it helps. Meanings are returned separately from interpretation: the tool hands back what was drawn and the procedure used, and the calling agent decides what to do with it.
Part of Pipeworx — an MCP gateway connecting AI agents to 1863+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.
Part of the Pipeworx "chance" family — a shared seeded-RNG and session engine
also used by dice-roller, tarot, i-ching and random-tables
(see docs/chance-packs-plan.md).
Tools
draw_constraint(count?, categories?, seed?, session_id?)— draws 1-10 cards, optionally restricted to one or more of the nine categories. Passseedto reproduce an exact draw later (same seed + count + categories always returns the same cards); omit it for a fresh random draw, and the seed actually used is returned. Passsession_idfrom a previous response to continue a no-repeat session (draw-without-replacement across calls).list_constraint_categories()— lists the nine categories, each with its card count and one example title.get_constraint(id)— fetches one specific card by its id (e.g."inversion_03").
Auth
Keyless. No upstream API, no third-party dependency.
Data sources
- Pipeworx — original creative-constraints deck. Every card's title,
constraint sentence and rationale is written for this pack; there is no
public-domain or commercial foundation behind it (unlike
tarot's Rider–Waite–Smith tradition ori-ching's Legge translation).
The nine categories
perspective, limitation, medium, time, audience, inversion,
scale, process, wildcard — 18 cards each, 162 total.
Sessions are hosted-only
draw_constraint's session_id support depends on the gateway's KV cache
binding (injectCacheKv: true on this pack's manifest row). The published npm
standalone has no such binding, so a session_id there (or from any caller
without the gateway's cache) gets session_supported: false in the response
and falls back to a plain seeded draw — fully reproducible by seed, just not
draw-without-replacement across separate calls. Sessions expire after 24
hours of inactivity.
Reproducibility
Every draw is seeded. Omit seed for a fresh random draw (the seed used is
always returned in meta.seed); pass that seed back, with the same count
and categories, to reproduce the exact same cards. When continuing an
existing session via session_id, the session keeps the category filter it
was opened with — categories is ignored on that call.
Errors
An unknown category in categories is a loud error listing the valid set.
An unknown id to get_constraint is a loud error with the id-naming
convention. An expired or unknown session_id is a loud error telling you to
omit it to start a new session.
Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"creative-constraints": {
"url": "https://gateway.pipeworx.io/creative-constraints/mcp"
}
}
}
What this endpoint actually serves
tools/list at https://gateway.pipeworx.io/creative-constraints/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1863+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
No MCP client? Call it over HTTP
curl -X POST https://gateway.pipeworx.io/v1/tools/draw_constraint \
-H 'Content-Type: application/json' \
-d '{"categories":["inversion"],"count":3,"seed":"pipeworx-demo"}'
No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/draw_constraint. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.
Run it from npm
@pipeworx/mcp-creative-constraints is a local stdio bridge to the Pipeworx gateway: your MCP client
starts it with npx, and it forwards every call to the same
https://gateway.pipeworx.io/creative-constraints/mcp endpoint shown above. It needs network access;
there is no offline mode.
{
"mcpServers": {
"creative-constraints": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-creative-constraints"]
}
}
}
Without a key it calls anonymously, capped at 50 calls a day. A free account
raises that to 200 a day: get a key at https://pipeworx.io/signup and add
"env": { "PIPEWORX_API_KEY": "<your key>" } to the server entry.
The key is sent as a Bearer token, the same way a hosted connection sends it,
so calls are metered and billed exactly as they are there.
It lists only this pack's tools by default. Set PIPEWORX_META_TOOLS=1 to
also list ask_pipeworx and the other gateway-wide tools.
Behind an HTTPS proxy: Node's built-in fetch does not read HTTPS_PROXY by
default. Newer Node releases honour it when NODE_USE_ENV_PROXY=1 is set; check
your Node version's documentation.
Using with ask_pipeworx
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Creative Constraints data" })
The gateway picks the right tool and fills the arguments automatically.
More
License
MIT
Reviews
No reviews yet
Be the first to review this server!
More Developer Tools MCP Servers
Rea
Freeby Morluto · Developer Tools
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Paperclip
Freeby Paperclipai · Developer Tools
Trending hip-hop artist momentum scores across four cultural dimensions.
Toleno
Freeby Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
MCP Marketplace
Freeby mcp-marketplace · Developer Tools
Search and install MCP servers from inside your AI client.
mcp-creator-python
Freeby mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.
by Lharries · Communication
Read, search, and send WhatsApp messages through your AI assistant
