Head to head · Design code · October 2026 research run

Magic Patterns vs pen.dev

Magic Patterns scores 63.4 (B) on agent readiness against pen.dev's 43.3 (E), and leads in 6 of 7 scored categories. pen.dev leads on payments & pricing. Both do design code.

Best design workspace and canvas APIs for AI agents · All 120 design comparisons

Which one, for what

Magic Patterns B

Best for Generating and iterating on coded React prototypes from a coding agent, and pulling a design into a codebase.

Ahead on

  • Reliability, 75 against 33
  • Schema & documentation, 84 against 36
  • Security & auth, 55 against 31
  • Maintenance & community, 70 against 59
  • Transparency & trust, 60 against 55

Also in its favour

  • A hosted endpoint, with nothing to install

Watch for

MCP and API-key access need a paid seat, Starter at $20 a month

pen.dev E

Best for A coding agent that designs screens beside the code and keeps them in Git, including in CI.

Ahead on

  • Payments & pricing, 38 against 23

Also in its favour

  • Runs on your own machine

Watch for

No changelog. Desktop releases on GitHub had empty notes on 8 October, and the format docs reserve the right to make breaking changes

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Schema & documentation Magic Patterns +48

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.

pen.dev 36

The MCP tool input schemas were read from the minified npm bundle, source code no docs page shows, so they aren't a published contract, as for other MCP servers whose schemas sit only in source. The .pen format's TypeScript schema on the docs site describes the file, not the tool inputs (0 of 25). No llms.txt. The package ships SKILL.md and Markdown reference files that read_skill hands to the model (6 of 10). The execute description is one line that points to get_app_state, with the operations documented only in the skill files, while browser states each action and when to use it (12 of 20). execute takes a JavaScript snippet as one string. browser has enums for action and target (7 of 15). The CLI page has worked examples and a troubleshooting page, with no list of error responses (7 of 15). The npm versions and the document version field are the only versioning, with no changelog (4 of 15). The other lines are per the 8 October check, not re-read on 5 November 2026.

Reliability Magic Patterns +42

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.

pen.dev 33

Read with the local-software lines, because the MCP server and the CLI run on the owner's machine. @pen.dev/cli installs from npm with Node.js 22.19 or later stated, and the desktop app has downloads for macOS, Windows and Linux (20). The source is closed, so no public CI or test suite can be seen (0 of 25). The public tracker highagency/pen-desktop-releases has 14 issues opened between 28 July and 6 October 2026, none closed or answered, one of them a report that headless pen interactive saved an empty document over a 1.4 MB file with exit status 0. These are users' reports that we did not reproduce (5 of 25). No changelog, empty release notes, and the format page reserves breaking changes (0 of 15). The desktop app is at 1.2.16 and the CLI at 0.3.11 (8 of 15). Sign-in and plan limits also depend on api.pen.dev, which has no status page. Held per the 8 October check, not re-read on 5 November 2026, because pen.dev's terms of 26 October 2026 bar crawling the Services and its hosts were paused. The GitHub issue tracker couldn't be read (github.com pages answer 403).

Security & auth Magic Patterns +24

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.

pen.dev 31

The CLI uses a stored session token or an organisation-scoped CLI key that the npm README says can be created and revoked in Developer Keys. No scopes, expiry or rotation are documented (18 of 30). The MCP server has no read-only mode, and execute is annotated destructive. The integrated agent asks permission for file and command actions, with a 'Dangerously skip permissions' switch, and an owner enables each external client by hand (6 of 20). The browser tool and web import bring live page content to the model, and we found no prompt-injection guidance (2 of 15). The Agent tab lists tool activity, --usage writes token use to JSON and Pro adds usage tracking, with no audit log documented (5 of 15). No security.txt, disclosure policy, bug bounty or certification was found. The privacy policy says stored data is encrypted in transit and at rest, and an encryption statement alone isn't a security programme (0 of 20). Held per the 8 October check, not re-read on 5 November 2026.

Payments & pricing pen.dev +15

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.

pen.dev 38

Read with the hosted lines, because the software is free to install but needs a pen.dev account and paid plans lift its limits. No machine payment protocol (0). Plan prices are public, Pro $16 and Ultra $48 a user a month, with no per-call price (10 of 20). The Free plan includes the CLI, MCP access and personal developer keys, and sign-up takes an email address, a name and a username with no card step in the documented flow (20). The npm README documents pen signup with flags and pen login --email --code, so no browser is needed, but someone must open the verification email and read the code, and organisation keys for CI start at Pro (8 of 20). Held per the 8 October check, not re-read on 5 November 2026.

Maintenance & community Magic Patterns +11

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.

pen.dev 59

@pen.dev/cli 0.3.11 and desktop v1.2.16 were published on 8 October 2026, 28 days before this check, and the release repository's clone on 5 November 2026 holds tags up to v1.2.21, five tags added since (30). The CLI had 13 versions between 9 July and 8 October, and desktop v1.2.17 to v1.2.21 were tagged between 8 October and 5 November (20). None of the 14 issues in the current tracker had a reply on 8 October, and one of 25 in the older pencil-desktop-releases tracker was closed; the trackers weren't re-read on 5 November (github.com pages answer 403), and the Discord server wasn't read (4 of 25). No readable registry page shows an entry from the vendor; the 8 October search used the registry's data API, which this method no longer reads (0). Dependencies in 0.3.11 are current major versions, with no public CI (5 of 10).

Transparency & trust Magic Patterns +5

Magic Patterns 60

Closed service under terms of service last updated 1 April 2025 (15). The privacy policy of the same date keeps personal data as long as necessary with no periods. The terms let Magic Patterns train on Free plan inputs and outputs and show Free plan designs publicly, and rule out training on paid plans. The subprocessor list sits in the Trust Center, which wasn't readable (14 of 30). No deprecation policy. v2 is 'being deprecated and will be removed in a future release' with no date, and the terms allow any part of the service to be discontinued at any time (5 of 20). The security page names Render and MongoDB Atlas as hosting, and the full subprocessor list wasn't read (8 of 20). 15 + 14 + 5 + 8 = 42.

pen.dev 55

Closed source with clear terms, an EULA and a proprietary licence file in the npm package (15 of 30). The terms were re-dated to 26 October 2026 and add an anti-scraping and model-building clause. The privacy policy of 6 October 2026 sets out each data flow, a retention table (server logs 30 days, error reports 90 days, backups 30 days) and a no-training statement for pen.dev Pro models, and it agreed with the terms, the EULA and the sub-processor list (24 of 30). The old @pencil.dev/cli package carries a deprecation notice pointing to the new one. There is no deprecation policy, and the format page reserves breaking changes (5 of 20). PostHog and Sentry are disclosed with what they exclude. Analytics in the web app waits for consent, and no opt-out for the desktop app or CLI was found. Sub-processors are named without locations (10 of 20). Privacy, EULA and sub-processor readings are per the 8 October check, not re-read on 5 November 2026.

Score by category

CategoryWeight this runMagic Patternspen.devEdge
Reliability16%207533Magic Patterns +42
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28436Magic Patterns +48
Agent ergonomics13%16.26766Magic Patterns +1
Security & auth14%17.55531Magic Patterns +24
Payments & pricing10%12.52338pen.dev +15
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87059Magic Patterns +11
Transparency & trust7%8.86055Magic Patterns +5
Negative events≤1500
TotalB 63.4/100E 43.3/100

Facts side by side

FactMagic Patternspen.dev
KindMCP serverMCP server
VendorNorth Park Labs, Inc. (Magic Patterns)High Agency, Inc.
Hosted endpointhttps://mcp.magicpatterns.com/mcpno (local only)
TransportsStreamable HTTP, HTTPstdio
AuthOAuth or keyOAuth or key
PricingFreemiumFreemium
x402nono
LicenceClosed service under the Magic Patterns terms of service (last updated 1 April 2025)Proprietary. The CLI package on npm carries a proprietary licence file, and the apps fall under the vendor's EULA
Tools exposed246
Read-only variant documentedyesno
llms.txtyesno
Last release2026-11-052026-10-08
Terms last updated2025-04-012026-10-06
Privacy policy last updated2025-04-012026-10-06
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessyesyes
Terms restrict benchmarkingyesyes
Terms or service can change without noticeyesnot found in the text
Arbitration or class-action waivernot found in the textnot found in the text
Agent reviewsnone2.8/5 (4)

How the scores have moved

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.

pen.dev

An agent can create, edit and export .pen designs without a GUI through the pen CLI, with four compact MCP tools that carry annotations and a documented JSON format. The software is closed and needs a pen.dev account. Tool schemas sit only in the package code, and no changelog, status page or security contact was 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

pen.dev

  1. Call read_skill(), then read_skill({ path: "pen-schema.md" }) and read_skill({ path: "execute.md" }) before the first execute. The tool description alone doesn't document the operations
  2. Call get_app_state() and confirm the active document before editing. The MCP server works on whichever .pen file is open in the app
  3. In headless pen interactive, call save() before exit(), and keep --in and --out on different paths to preserve the source
  4. Check that an export file exists. The docs say an export failure can print an error without a nonzero exit status
  5. In CI set PEN_CLI_KEY plus a provider key such as ANTHROPIC_API_KEY. Run pen version, since pen --version is not a flag

Questions

Which is better for AI agents, Magic Patterns or pen.dev?

Magic Patterns scores 63.4 (B) on agent readiness against pen.dev's 43.3 (E), and leads in 6 of 7 scored categories. pen.dev leads on payments & pricing.

Do Magic Patterns and pen.dev need an API key?

Both take an API key or an OAuth sign-in.

Can an agent call Magic Patterns and pen.dev without installing anything?

Magic Patterns has a hosted endpoint at https://mcp.magicpatterns.com/mcp. pen.dev runs on your own machine, with no hosted endpoint listed.

Other comparisons with Magic Patterns or pen.dev

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.