Blender integration through the Model Context Protocol
Tangent is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Hand-picked design references, UI patterns and the people behind them, each with why it fits.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http tangent-mcp https://tangent.directory/api/mcp
# 2 — ask your agent for something these tools do
# find_inspiration, search_resources, browse_vertical and 7 more
Tangent costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http tangent-mcp https://tangent.directory/api/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
10 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Turns a design brief into a short list of references (default 8, at most 10), each with why it fits: the pattern, style, category, technology or platform it shares with the brief, or how search matched it (e.g. "similar meaning"). It reads the brief against Tangent's taxonomy and synonyms and combines that with search; no AI calls. Use it when someone describes a screen or product they are about
| Parameter | Type | Required | Notes |
|---|---|---|---|
| brief | string | yes | What you are designing, in plain words, e.g. "onboarding for a fintech app, playful but clean". |
| platform | string | no | Prefer resources for this platform: "web", "mobile" or "desktop". |
| limit | integer | no | How many picks (1 to 10, default 8). |
Ranked search over Tangent's catalogue of design and design-engineering resources (sites, products, component libraries, tools, articles). Use it when you know roughly what you want; narrow with vertical, category, technology, type, pricing or open_source, and page with cursor. For a whole brief, use find_inspiration. Example: {"query": "command menu", "technology": "react", "limit": 5}
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | What to look for, e.g. "command menu" or "dark dashboard". |
| vertical | string | no | Section: "inspiration", "components", "motion", "build", "visuals", "tools" or "learn". |
| category | string | no | Category slug or name, e.g. "finance", "component-libraries", "typography". |
| technology | string | no | Technology slug or name, e.g. "react", "tailwind-css", "three-js". |
| type | string | no | Resource type, e.g. "website", "product", "library", "tool", "gallery", "article". |
| pricing | string | no | Pricing model. |
| open_source | boolean | no | true: only open-source resources; false: only ones known not to be. |
| limit | integer | no | Results per page (1 to 50, default 10). |
| cursor | string | no | next_cursor from the previous call, with the same query and filters. Omit for the first page. |
The newest resources in one section: inspiration, components, motion, build, visuals, tools or learn. Use it to browse without a query, with the same filters as search_resources and cursor paging. Example: {"vertical": "components", "technology": "react", "limit": 20}
| Parameter | Type | Required | Notes |
|---|---|---|---|
| vertical | string | yes | Section: "inspiration", "components", "motion", "build", "visuals", "tools" or "learn". |
| category | string | no | Category slug or name, e.g. "finance", "component-libraries", "typography". |
| technology | string | no | Technology slug or name, e.g. "react", "tailwind-css", "three-js". |
| type | string | no | Resource type, e.g. "website", "product", "library", "tool", "gallery", "article". |
| pricing | string | no | Pricing model. |
| open_source | boolean | no | true: only open-source resources; false: only ones known not to be. |
| limit | integer | no | Results per page (1 to 50, default 20). |
| cursor | string | no | next_cursor from the previous call, with the same query and filters. Omit for the first page. |
Everything Tangent knows about one resource: descriptions, taxonomy, editorial notes, the people behind it, and its related resources (tangents) with reasons. Use it to go deeper on a search pick. Set include_image to also get a small screenshot. Example: {"slug": "linear"}
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | Resource slug, e.g. "linear". |
| include_image | boolean | no | Also attach a small WebP thumbnail (under ~100 KB) as an image block. Off by default to save tokens. |
Resources related to one resource, each with the reason (e.g. "shares Command Menu", "same maker"). Use it to follow tangents from a site you like. Example: {"slug": "stripe"}
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | Resource slug, e.g. "stripe". |
Every UI and interaction pattern resources are filed under (Command Menu, Onboarding, Empty State and more), with example counts. Use it to pick a slug for get_pattern. Example: {}
No parameter schema on file.
One UI pattern: its definition, its best examples, related patterns and the technologies the examples use. Use it before designing that pattern. Example: {"slug": "empty-state", "limit": 8}
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | Pattern slug, e.g. "command-menu" or "empty-state". |
| limit | integer | no | How many examples to return (1 to 60, default 12). |
Find designers and design engineers by name, role, focus or stack, ranked, with optional technology and role filters. Example: {"query": "motion", "role": "design engineer"}
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Name, role, focus or stack, e.g. "motion" or "Rauno". |
| technology | string | no | Only people whose site is built with this technology, e.g. "nextjs", "astro", "framer". |
| role | string | no | Words in their role, e.g. "design engineer" or "product designer". |
| limit | integer | no | Results per page (1 to 50, default 10). |
| cursor | string | no | next_cursor from the previous call, with the same query and filters. Omit for the first page. |
Designers and design engineers in the catalogue, featured first, then by name, with optional technology and role filters and cursor paging. Use search_people to find someone by name or focus. Example: {"role": "design engineer", "technology": "nextjs", "limit": 20}
| Parameter | Type | Required | Notes |
|---|---|---|---|
| technology | string | no | Only people whose site is built with this technology, e.g. "nextjs", "astro", "framer". |
| role | string | no | Words in their role, e.g. "design engineer" or "product designer". |
| limit | integer | no | Results per page (1 to 50, default 20). |
| cursor | string | no | next_cursor from the previous call, with the same query and filters. Omit for the first page. |
One person's profile: role, bio, website, social links, studios, what their site is built with (confirmed technologies) and their work on Tangent. Set include_image to also get a small preview of their site. Example: {"slug": "emil-kowalski"}
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | Person slug, e.g. "rauno-freiberg". |
| include_image | boolean | no | Also attach a small WebP thumbnail (under ~100 KB) as an image block. Off by default to save tokens. |
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Tangent or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither. So there is no grade — not a withheld one, an unmeasured one.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 0.2.0.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish Tangent can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.