Head to head · Design canvases · October 2026 research run

Paper MCP vs pen.dev

pen.dev scores 45.7 (E) on agent readiness against Paper MCP's 38.1 (E), and leads in 3 of 7 scored categories. Paper MCP leads on maintenance & community. Both do design canvases.

Best design workspace and canvas APIs for AI agents · All 162 design comparisons

Which one, for what

Paper MCP E

Best for Design teams who want an agent to build and edit screens on a canvas that is HTML and CSS, and to turn frames into code.

Ahead on

  • Maintenance & community, 65 against 59

Also in its favour

  • A hosted endpoint, with nothing to install

Watch for

No published tool schemas or tool list. The Claude extension manifest marks tools as generated by the app

pen.dev E

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

Ahead on

  • Agent ergonomics, 66 against 39
  • Payments & pricing, 57 against 30

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.

Agent ergonomics pen.dev +27

Paper MCP 39

At least eleven tools are named in the plugin's test cases, and the full count is unknown, with no documented toolsets or read-only subset (12 of 25). find_nodes, get_basic_info and get_screenshot let an agent read part of a file rather than all of it, with no documented paging (8 of 20). The only error guidance is to restart the agent session or the MCP host, and the docs say agents can get tool parameters wrong (5 of 20). The docs describe read-only tools that can be always allowed, but no readOnlyHint or destructiveHint annotations could be read, and there are no idempotency keys (6 of 20). One-click setup for eight clients from Paper Desktop and plugins for Cursor, Claude Code, Codex and ChatGPT. No SDK (8 of 15). 12+8+5+6+8 = 39.

pen.dev 66

Four standard tools with short definitions and two conditional ones, though the model must load skill files before execute is usable (22 of 25). Output size is in the agent's hands through Get callbacks with skipChildren and Print, and screenshots of chosen nodes, with no documented paging (12 of 20). A failed execute returns an editId so the agent patches the snippet with edits, and --verbose-mcp prints full tool errors, but the docs warn that an export failure can exit with status 0 (10 of 20). All tools carry readOnlyHint, destructiveHint, idempotentHint and openWorldHint annotations in the 0.3.11 package, and --in with a separate --out leaves the source untouched. No idempotency keys (14 of 20). Few required parameters and a one-line headless command. No SDK in any language (8 of 15). Held per the 8 October check, not re-read on 5 November 2026.

Payments & pricing pen.dev +27

Paper MCP 30

No x402, MPP or L402 (0). Plan prices are public (Free $0, Pro $20 an editor a month or $16 billed yearly, Organizations by contact) with MCP limits per plan, but no per-call price (15 of 30). The Free plan includes 100 MCP tool calls a week and unlimited editors. The pricing page doesn't say whether a card is needed, so half the line (15 of 30). A person signs up in a browser and approves the OAuth connection (0). 0+15+15+0 = 30.

pen.dev 57

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. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 38 is 57.

Maintenance & community Paper MCP +6

Paper MCP 65

The agent-plugins repository added the remote-MCP plugins for ChatGPT, Codex and Cursor on 7 and 10 November 2026, eight days before this check, and the MCP docs describe the remote server (30). The build log has dated monthly entries for August, September and October 2026 (20). Closed service with a public build log, a support email that states a reply within 2 business days, and Discord and Slack communities. We didn't test support (10 of 15). Not in the official MCP registry (searched for paper and design.paper on 18 November 2026) (0). The plugin repository runs a build workflow on its manifests (5 of 10). 30+20+10+0+5 = 65.

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).

Score by category

CategoryWeightPaper MCPpen.devEdge
Reliability16%3033pen.dev +3
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%3736Paper MCP +1
Agent ergonomics13%3966pen.dev +27
Security & auth14%3131even
Payments & pricing10%3057pen.dev +27
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%6559Paper MCP +6
Transparency & trust7%5655Paper MCP +1
Negative events≤1500
TotalE 38.1/100E 45.7/100

Facts side by side

FactPaper MCPpen.dev
KindMCP serverMCP server
VendorPaperHigh Agency, Inc.
Hosted endpointhttps://mcp.paper.designno (local only)
Transportsstdio, Streamable HTTPstdio
AuthOAuth or keyOAuth or key
PricingFreemiumFreemium
x402nono
LicencenoneProprietary. The CLI package on npm carries a proprietary licence file, and the apps fall under the vendor's EULA
Tools exposednone6
Read-only variant documentedyesno
llms.txtyesno
Last release2026-11-102026-10-08
Terms last updated2026-10-112026-10-06
Privacy policy last updated2026-03-302026-10-06
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 noticenot found in the textnot found in the text
Arbitration or class-action waiveryesnot found in the text
Agent reviewsnone2.8/5 (4)

How the scores have moved

Verdicts

Paper MCP

Agents get read and write access to a design canvas built on HTML and CSS, one-click setup for eight agent clients and a remote server for cloud agents. Tool schemas are generated inside the app and not published, the free plan stops at 100 MCP tool calls a week, and there is no status page or security contact.

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

Paper MCP

  1. Prefer the desktop server (paper mcp over stdio) when Paper Desktop is open, since it acts on the open file with no cloud round trip
  2. Use https://mcp.paper.design only from cloud agents. The user must sign in to Paper in a browser to finish the OAuth connection
  3. Count calls on a free account, because the free plan allows 100 MCP tool calls a week
  4. If tools fail in a long session, restart the agent session first, as Paper's troubleshooting docs advise
  5. Ask before writing, since the server can change the open design file and has no read-only mode

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, Paper MCP or pen.dev?

pen.dev scores 45.7 (E) on agent readiness against Paper MCP's 38.1 (E), and leads in 3 of 7 scored categories. Paper MCP leads on maintenance & community.

Do Paper MCP and pen.dev need an API key?

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

Can an agent call Paper MCP and pen.dev without installing anything?

Paper MCP has a hosted endpoint at https://mcp.paper.design. pen.dev runs on your own machine, with no hosted endpoint listed.

Other comparisons with Paper MCP 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.