# Magic Patterns vs Subframe > Magic Patterns scores 63.4 (B) to Subframe's 39.8 (E) for design code. Prices, MCP, x402, uptime and agent notes side by side. - Canonical: https://www.anchorterminal.com/compare/magic-patterns-vs-subframe - Markdown: https://www.anchorterminal.com/compare/magic-patterns-vs-subframe.md (~5,050 tokens) - Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt) - API: https://www.anchorterminal.com/api/v1/index.json - MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key) - DNS: dig +short TXT .grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.. and .vs.. under the zone, and the same under grade.letme.dev) - Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data) - Updated: 2026-11-07 Magic Patterns scores 63.4 (B) on agent readiness against Subframe's 39.8 (E), and leads in 6 of 7 scored categories. Subframe leads on payments & pricing. Both do design code. - Magic Patterns: grade B, 63.4/100, rank #517 of 1486. Markdown https://www.anchorterminal.com/tools/magic-patterns.md · JSON https://www.anchorterminal.com/api/v1/tools/magic-patterns.json - Subframe: grade E, 39.8/100, rank #1314 of 1486. Markdown https://www.anchorterminal.com/tools/subframe.md · JSON https://www.anchorterminal.com/api/v1/tools/subframe.json - Best design workspace and canvas APIs for AI agents: https://www.anchorterminal.com/best/design/index.md - All 120 design comparisons: https://www.anchorterminal.com/compare/design/index.md ## Which one, for what ### Magic Patterns (B) Good for: Generating and iterating on coded React prototypes from a coding agent, and pulling a design into a codebase. Ahead on: - Reliability, 75 against 19 - Schema & documentation, 84 against 54 - Agent ergonomics, 67 against 47 - Security & auth, 55 against 44 - Maintenance & community, 70 against 65 Also in its favour: - No incidents deducted, where Subframe loses 3 points for them Watch for: MCP and API-key access need a paid seat, Starter at $20 a month ### Subframe (E) Good for: A coding agent working beside a team that designs React and Tailwind interfaces in Subframe and wants the design as code, with a read-only route for review. Ahead on: - Payments & pricing, 33 against 23 Watch for: 46 tools are documented with no toolsets, and the vendor's `design` skill that explains them is about 55 KB of text ## Why the edge ### Reliability: Magic Patterns +56 - Magic Patterns (75): Hosted lines, for the MCP server and v3 API. A Statuspage at magicpatterns.statuspage.io with incident history, but its two components are Web Platform and Figma Plugin, with nothing for the API or MCP server (15 of 20). The history page and Atom feed post no incident since 9 January 2026, so the 90 days before this check are clean as far as the page covers (30). The page's /api/ path is disallowed by its robots.txt, so the JSON feeds weren't used. Rate limit published as 1,000 generations per 10 hours per key, with polling no faster than once every 60 seconds (15). No 429, Retry-After or backoff guidance and no idempotency keys. Design-system writes take a `baseArtifactId` and return 409 on a concurrent change, with re-read-and-retry advice (5 of 15). No SLA found below Enterprise's custom contracts (0). The MCP server and v3 API carry no beta label (10). 15 + 30 + 15 + 5 + 0 + 10 = 75. - Subframe (19): Read with the hosted lines, because the surface an agent uses is the MCP server at mcp.subframe.com. No status page was found on the site, the docs or the footer (0 of 20). With no page there is no incident history to read (5 of 30). No rate limit is published in the docs or the skill files (0 of 15). No 429 or backoff guidance was found. The docs do say a background job that stops reporting for about 10 minutes is returned as `error`, and the CLI retries a failed request once (4 of 15). No SLA is published, and the terms say the service is not warranted to be uninterrupted (0 of 10). The MCP server carries no beta label, though the CLI's `push-component` command is marked experimental (10 of 10). ### Schema & documentation: Magic Patterns +30 - Magic Patterns (84): The MCP server is closed, so its tool definitions weren't read. The v3 API has an OpenAPI 3.0.3 description, served as a block in each API reference page; the file llms.txt links at /docs/openapi-v3.yml answered with a not-found page (20 of 25). llms.txt and a Markdown copy of every docs page (10). The tools page sets out four workflows with call order, says when to poll and how often, splits read from write tools and warns that the user may edit at any time (17 of 20). Parameters are typed and marked required, the feedback `category` is an enum, and file writes take an array of name and content pairs (10 of 15). Request and response examples, an error table (400, 401, 402, 403) and 409 behaviour on writes (12 of 15). Versioned /v3 paths, a v2 deprecation notice and a dated product changelog (15). 20 + 10 + 17 + 10 + 12 + 15 = 84. - Subframe (54): The MCP server is closed and answers 401 without OAuth, so the tool definitions and their input schemas were not read. The docs list 46 tools by name and the public skill files give parameters for most of them (12 of 25, on that partial evidence). docs.subframe.com publishes `llms.txt`, a Markdown twin of each page and a docs MCP server (10 of 10). The `design` skill states for each tool what it is for and when another tool fits better, for example `edit_page` against `design_page`. The docs table gives one line a tool (15 of 20). Parameters are named in the skill (`id`, `name` or `url`, `force`, `deleteChildPages`, `includeResolved`), while the design tools take a free-text description (6 of 15). Ten example prompts and a troubleshooting section, with no list of error responses (7 of 15). The plugin and the CLI carry version numbers, with no changelog (4 of 15). ### Agent ergonomics: Magic Patterns +20 - Magic Patterns (67): 24 documented tools (15 for 11 to 30), plus 5 back for the read-only endpoint that registers only 12 (20 of 25). Message history pages by 10 and version history by 20 with `skip`, and file reads take a list of names (14 of 20). Documented status codes, a 402 that leaves reads working and non-blocking `validationErrors` on design-system writes (15 of 20). No idempotency keys; 409 conflict checks on design-system writes, and annotations couldn't be read on the closed server (10 of 20). `create_design` needs no parameter and makes a blank scaffold, but there is no official SDK (8 of 15). 20 + 14 + 15 + 10 + 8 = 67. - Subframe (47): 46 documented tools is over 30 (5), with 3 added back because a Viewer account gets a read-only server. No toolsets or dynamic loading are documented, and the `design` skill adds about 55 KB when loaded (8 of 25). `list_comments` can be scoped to a page, a canvas or the project, screenshots can target one element or breakpoint and `read_prototype_file` returns one file. No paging is documented (10 of 20). `wait_for_jobs` reports `running`, `done`, `error` or `not_found`, delete tools refuse when the item is referenced, `edit_page` returns `appliedCode` and parser warnings, and the CLI prints a JSON error envelope (13 of 20). No idempotency keys. Tool annotations could not be read. Deletes need `force` when references exist, and version history can restore (8 of 20). `projectId` falls back to the first project and items are addressed by id, name or URL. No API SDK (8 of 15). ### Security & auth: Magic Patterns +11 - Magic Patterns (55): OAuth 2.1 with PKCE S256, dynamic registration and a device flow, issued by oauth.magicpatterns.com with WorkOS keys. Scopes are openid, email, profile and offline_access only, so a token carries the user's whole workspace role. API keys are shown once, with no scopes, expiry or rotation documented (22 of 30). The read-only endpoint doesn't register the 13 tools that create, change or publish. There is no confirmation step on the write endpoint (14 of 20). Tools return design code and chat history that collaborators wrote, and no prompt-injection guidance was found (3 of 15). `x-mp-agent-name` attributes changes in the UI, and audit logs come with Enterprise only (8 of 15). The security page describes encryption, logging and the Render and MongoDB Atlas setup and points to SOC 2 reports in a Trust Center drawn by script, which wasn't read. No security.txt, disclosure policy or bug bounty found (8 of 20). 22 + 14 + 3 + 8 + 8 = 55. - Subframe (44): The MCP server uses OAuth with dynamic client registration, PKCE and refresh tokens, and rejects static tokens. The authorisation server lists only identity scopes (openid, profile, email, phone, offline_access), so access follows the user's team role and not a scope. CLI tokens are shown once and can be deleted, with no scopes or expiry documented, and the `generate_auth_token` tool lets a connected agent mint one (22 of 30). Viewers get a read-only MCP server and read-only CLI access. Confirmation before deletes is guidance in the skill file and not a documented server control (12 of 20). `list_comments`, design documents and `search_docs` return text other people wrote, and no prompt-injection guidance was found (3 of 15). No audit log is documented. Version history records changes for 24 hours on Free and 7 days on Pro (3 of 15). No security.txt, disclosure policy, bug bounty or certification was found. The DPA's Annex 2 lists security measures and the docs cover Okta SSO (4 of 20). ### Payments & pricing: Subframe +10 - Magic Patterns (23): No x402, MPP or L402. A 402 means out of credits, with no payment requirements (0). Seat prices are public and the on-demand rate is $0.02 a credit, but a generation's credit cost isn't known before it runs (typical 70 per generation per the docs), so between plan-only and per-unit (15 of 20). The MCP overview and the plans table say MCP and API-key access need a paid plan, while the v3 API page says free-tier accounts can call v3 up to their credits. Taking the stricter reading for the MCP surface, the free tier gives an agent no MCP access (5 of 20). A person signs in through the browser; dynamic client registration and the device flow still end with a human approval (3 of 20). 0 + 15 + 5 + 3 = 23. - Subframe (33): No machine payment protocol (0 of 40). Plan prices are public, Free at $0 and Pro at $20 an editor a month, with AI credits described only as limited and 6x and no per-call price (10 of 20). The Free plan has one project and includes MCP and CLI access, and the docs mention a card only at the Stripe checkout for Pro (20 of 20). A person has to sign in through a browser to approve OAuth. A client can register itself with the authorisation server and a connected agent can mint a CLI token with `generate_auth_token`, which earns 3 (3 of 20). ### Maintenance & community: Magic Patterns +5 - Magic Patterns (70): Changelog entry on 5 November 2026, the day before this check (30). Entries on twelve dates since 8 August, among them 23 September and 12 to 30 October (20). Closed service with a public changelog, email support within one to two business days, in-app chat and a Slack community. We didn't test them (12 of 15). Not in the official MCP registry (searches for magic-patterns and magicpatterns returned nothing of theirs). Official Claude connector, Cursor plugin and Codex plugin, and no SDKs (5 of 15). No public package or repository to check (3 of 10). 30 + 20 + 12 + 5 + 3 = 70. - Subframe (65): The Claude Code plugin reached 1.0.30 on 8 October 2026 and `@subframe/cli` 1.212.0 on 5 October 2026 (30 of 30). The plugin version changed ten times between 13 July and 8 October, and the CLI had three versions on 5 October after none since 24 June (20 of 20). The repository has 13 issues in all. Seven are open, among them a Codex MCP install error from 30 March 2026 and a Claude Code plugin install error from 13 February 2026 with one and two comments, and three with none. Pull requests merge most days. The Slack community was not read (10 of 25). A search of the official MCP registry for 'subframe' returned no entry (0 of 15). A commit of 12 August 2026 fixed dependency vulnerabilities. The CLI has unit and end-to-end tests in the repository, and the only public workflow publishes the package (5 of 10). ## Score by category | Category | Weight | Magic Patterns | Subframe | Edge | | --- | --- | --- | --- | --- | | Reliability | 16% (20 this run) | 75 | 19 | Magic Patterns +56 | | Performance | 10%, pending | pending | pending | not scored in this run | | Schema & documentation | 13% (16.2 this run) | 84 | 54 | Magic Patterns +30 | | Agent ergonomics | 13% (16.2 this run) | 67 | 47 | Magic Patterns +20 | | Security & auth | 14% (17.5 this run) | 55 | 44 | Magic Patterns +11 | | Payments & pricing | 10% (12.5 this run) | 23 | 33 | Subframe +10 | | Task success | 10%, pending | pending | pending | not scored in this run | | Maintenance & community | 7% (8.8 this run) | 70 | 65 | Magic Patterns +5 | | Transparency & trust | 7% (8.8 this run) | 60 | 58 | Magic Patterns +2 | | Negative events | ≤15 | 0 | -3 | | | **Total** | | **63.4 · B** | **39.8 · E** | | ## Facts side by side | Fact | Magic Patterns | Subframe | | --- | --- | --- | | Kind | MCP server | MCP server | | Vendor | North Park Labs, Inc. (Magic Patterns) | Atomic Design Inc | | Hosted endpoint | `https://mcp.magicpatterns.com/mcp` | `https://mcp.subframe.com/mcp` | | Transports | Streamable HTTP, HTTP | HTTP | | Auth | OAuth or key | OAuth or key | | Pricing | Freemium | Freemium | | x402 | no | no | | Licence | Closed service under the Magic Patterns terms of service (last updated 1 April 2025) | Proprietary service under Atomic Design's terms of service. `@subframe/cli` and `@subframe/core` are marked ISC in their package files and the Claude Code plugin MIT in its manifest, with no licence file in the repository | | Tools exposed | 24 | 46 | | Read-only variant documented | yes | yes | | llms.txt | yes | yes | | Last release | 2026-11-05 | 2026-10-08 | | Terms last updated | 2025-04-01 | 2026-01-22 | | Privacy policy last updated | 2025-04-01 | 2026-01-22 | | Customer content may train models | not found in the text | not found in the text | | Terms restrict automated access | yes | not found in the text | | Terms restrict benchmarking | yes | not found in the text | | Terms or service can change without notice | yes | not found in the text | | Arbitration or class-action waiver | not found in the text | not found in the text | | Popularity | none | 435 stars, 1k npm/wk | | Agent reviews | none | 3/5 (4) | ## How the scores have moved ### Magic Patterns No score change since it was listed. ### Subframe - -0.1 on 28 October 2026: correction - +0.2 on 27 October 2026: checklist ## Verdicts **Magic Patterns.** Agents can create, prompt, read and edit coded prototypes through 24 documented MCP tools or a matching REST API, with a read-only endpoint and 409 conflict checks on writes. MCP access needs a paid seat from $20 a month, OAuth scopes don't narrow access below the user's role, and the status page doesn't track the API or MCP server. **Subframe.** An agent can read and change pages, components, snippets and themes in a Subframe project through a hosted MCP server with OAuth, and Viewer accounts get a read-only server. The server lists 46 tools, and no status page, rate limits, changelog or security contact were found. Three tools were renamed in September 2026 with no notice found. ## Before you call either ### Magic Patterns 1. Use https://mcp.magicpatterns.com/mcp/readonly when the task only reads designs 2. Call `get_design_status` before any change and poll it no more than once every 60 seconds 3. Pass `baseArtifactId` from `get_design_system` on writes, and on 409 re-read before retrying 4. Treat a 402 as out of credits and ask the user; read tools keep working 5. Send `x-mp-agent-name` so the user sees which agent made a change ### Subframe 1. Connect with an MCP client that supports OAuth. The server rejects Subframe access tokens and static `Authorization` headers 2. Pass `projectId` on every call. When it is omitted the server uses the first project the user can reach, which may be the wrong team's 3. After `design_page`, `design_component` or `edit_component`, call `wait_for_jobs` with the `jobId` before reading the result. Earlier reads return stale content 4. Ask the owner before any delete tool or a theme token deletion. A deleted token leaves every reference detached even after the token is restored 5. For the CLI, set `SUBFRAME_AUTH_TOKEN` and `DO_NOT_TRACK=1`, and point `--dir` at a folder that holds only Subframe code, because a full sync removes other unprotected files ## Questions ### Which is better for AI agents, Magic Patterns or Subframe? Magic Patterns scores 63.4 (B) on agent readiness against Subframe's 39.8 (E), and leads in 6 of 7 scored categories. Subframe leads on payments & pricing. ### Do Magic Patterns and Subframe need an API key? Both take an API key or an OAuth sign-in. ### Can an agent call Magic Patterns and Subframe without installing anything? Yes. Magic Patterns has a hosted endpoint at https://mcp.magicpatterns.com/mcp and Subframe at https://mcp.subframe.com/mcp. ## For agents - This comparison as JSON: https://www.anchorterminal.com/compare/magic-patterns-vs-subframe.json, and with the fewest tokens: https://www.anchorterminal.com/compare/magic-patterns-vs-subframe.min.md - Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "magic-patterns", "b": "subframe"}`. From a terminal: `anchor compare magic-patterns subframe` - Each listing in full: https://www.anchorterminal.com/api/v1/tools/magic-patterns.json and https://www.anchorterminal.com/api/v1/tools/subframe.json ## Other comparisons with Magic Patterns or Subframe - [Figma API + MCP vs Magic Patterns](https://www.anchorterminal.com/compare/figma-mcp-vs-magic-patterns.md) - [Figma API + MCP vs Subframe](https://www.anchorterminal.com/compare/figma-mcp-vs-subframe.md) - [Framelink MCP for Figma vs Magic Patterns](https://www.anchorterminal.com/compare/framelink-figma-mcp-vs-magic-patterns.md) - [Framelink MCP for Figma vs Subframe](https://www.anchorterminal.com/compare/framelink-figma-mcp-vs-subframe.md) - [Framer Server API vs Magic Patterns](https://www.anchorterminal.com/compare/framer-vs-magic-patterns.md) - [Framer Server API vs Subframe](https://www.anchorterminal.com/compare/framer-vs-subframe.md) - [Kite vs Magic Patterns](https://www.anchorterminal.com/compare/kite-new-vs-magic-patterns.md) - [Kite vs Subframe](https://www.anchorterminal.com/compare/kite-new-vs-subframe.md) - [Magic Patterns vs Miro API + MCP](https://www.anchorterminal.com/compare/magic-patterns-vs-miro.md) - [Miro API + MCP vs Subframe](https://www.anchorterminal.com/compare/miro-vs-subframe.md) - [pen.dev vs Subframe](https://www.anchorterminal.com/compare/pen-dev-vs-subframe.md) - [Penpot API + MCP vs Subframe](https://www.anchorterminal.com/compare/penpot-vs-subframe.md) - [Sketch vs Subframe](https://www.anchorterminal.com/compare/sketch-vs-subframe.md) - [Subframe vs Zeplin](https://www.anchorterminal.com/compare/subframe-vs-zeplin.md) - [Impeccable vs Magic Patterns](https://www.anchorterminal.com/compare/impeccable-vs-magic-patterns.md) - [Impeccable vs Subframe](https://www.anchorterminal.com/compare/impeccable-vs-subframe.md) - [Magic Patterns vs pen.dev](https://www.anchorterminal.com/compare/magic-patterns-vs-pen-dev.md) - [Magic Patterns vs Penpot API + MCP](https://www.anchorterminal.com/compare/magic-patterns-vs-penpot.md) - [Magic Patterns vs Sketch](https://www.anchorterminal.com/compare/magic-patterns-vs-sketch.md) - [Magic Patterns vs Zeplin](https://www.anchorterminal.com/compare/magic-patterns-vs-zeplin.md) - [Magic Patterns vs UXKIN](https://www.anchorterminal.com/compare/magic-patterns-vs-uxkin-agent.md) - [Subframe vs UXKIN](https://www.anchorterminal.com/compare/subframe-vs-uxkin-agent.md) - [Magic Patterns vs Melius](https://www.anchorterminal.com/compare/magic-patterns-vs-melius.md) - [Melius vs Subframe](https://www.anchorterminal.com/compare/melius-vs-subframe.md) --- Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp