Head to head · Design canvases · October 2026 research run

Paper MCP vs Penpot API + MCP

Paper MCP scores 38.1 (E) on agent readiness against Penpot API + MCP's 35.8 (F), and leads in 0 of 7 scored categories. Penpot API + MCP leads on reliability, schema & documentation, payments & pricing, maintenance & community and transparency & trust. 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.

Also in its favour

  • Runs on your own machine
  • No incidents deducted, where Penpot API + MCP loses 15 points for them

Watch for

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

Penpot API + MCP F

Best for Teams that want design files on their own servers and an agent working alongside a person in the editor.

Ahead on

  • Reliability, 44 against 30
  • Schema & documentation, 66 against 37
  • Payments & pricing, 45 against 30
  • Maintenance & community, 76 against 65
  • Transparency & trust, 71 against 56

Also in its favour

  • Free to start without a card
  • Open source

Watch for

Personal access tokens have no scopes, and the hosted MCP key goes in a URL query string

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 Penpot API + MCP +29

Paper MCP 37

The MCP tool definitions are generated by the app (tools_generated: true in the Claude extension manifest) and no page publishes their input schemas. The remote endpoint asks for OAuth before initialize, so no tool list was read. paper.design/openapi.json covers only two unauthenticated website endpoints and says the agent surface is the MCP server, not a REST API (0 of 25). llms.txt with a developer section (10). The MCP docs explain when to use the desktop server or the remote one, and say read tools are safe to always allow while write tools change the file, but the tool descriptions themselves were not readable (8 of 20). Tool names are known only from the ChatGPT plugin's review test cases (open_file, get_basic_info, get_screenshot, create_artboard, write_html, find_nodes, set_text_content, get_computed_styles and others), with no types (3 of 15). Example prompts and a troubleshooting section, with no list of error responses (6 of 15). A monthly dated build log, and plugin versions in the agent-plugins repository (10 of 15). 0+10+8+3+6+10 = 37.

Penpot API + MCP 66

The integration guide links generated API docs at design.penpot.app/api/_doc, and the backend's page template at 2.18.6 links a Swagger/OpenAPI description, but design.penpot.app's robots.txt disallows /api/ for every crawler, so neither page can be read and neither counts here. Every MCP tool in @penpot/mcp declares a typed zod input schema (read from the source at 2.18.6), which meets the line for MCP (25). No llms.txt (help.penpot.app/llms.txt answered 404 on 5 November). The MCP server's high_level_overview and penpot_api_info tools hand the model its docs instead (3 of 10). RPC docs are generated with little prose. MCP descriptions are long and tell the model to read the overview before execute_code (12 of 20). RPC inputs are typed, but the main MCP tool takes one JavaScript string (9 of 15). A curl example for get-profile. No documented error format, and the integration guide still says 'we do not have any specific documentation for the webhooks yet' (5 of 15). CHANGES.md per release (12 of 15).

Payments & pricing Penpot API + MCP +15

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.

Penpot API + MCP 45

No machine payment protocol (0). Plan prices are public, Unlimited $7 an editor a month capped at $175 and Enterprise $25 a member, with no per-call price (10 of 20). The cloud Professional plan is free with no card (20). A person signs up and creates the token or MCP key in account settings (0). Self-hosting the community edition is free under MPL-2.0. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 30 is 45.

Transparency & trust Penpot API + MCP +15

Paper MCP 56

Closed service with clear terms from Lost Coast Labs, Inc. (dba Paper), last updated 11 October 2026 (15). The privacy policy (30 March 2026), the terms and a DPA agree on who processes what. The terms let Paper use usage data, including telemetry, to improve the service and exclude customer content from that. No retention period was found in the privacy policy (18 of 30). The MCP docs announced the move from the localhost HTTP endpoint and kept it working, but there is no deprecation policy (8 of 20). A dated list of 16 subprocessors with their purposes, including PostHog for product analytics and Sentry for errors, without processing locations (10 of 20). 15+18+8+10 = 51.

Penpot API + MCP 71

MPL-2.0, including the MCP server (30). The privacy policy, last updated 5 August 2025 and now served at /privacy-policy, names Kaleidos, PostHog and Google Analytics, keeps data 'as long as the commercial relationship is maintained', points to a DPA in the terms and says nothing about AI training or data locations (15 of 30). Changes land in CHANGES.md and the separate penpot-mcp repository was archived with a pointer, but there's no deprecation policy. The removal of legacy SSE from the MCP server is now listed under the unreleased 2.19.0 heading, and released 2.18.6 still serves /sse (8 of 20). Self-hosted telemetry is off by default and documented as an opt-in flag (enable-telemetries) in the configuration guide (read from the docs source in the repository clone), which meets the line for the self-hosted half (20). The cloud names some processors without locations (8). (20 + 8) / 2 = 14 of 20.

Reliability Penpot API + MCP +14

Paper MCP 30

Read with the local-software lines, because the main surface is the stdio server the Paper CLI runs on the owner's machine (paper mcp), with Paper Desktop installed from paper.design/downloads. The Claude extension manifest lists macOS, Windows and Linux, while llms.txt names a macOS download, and no runtime requirements are stated (15 of 20). The app and server are closed, so no public CI or test suite can be seen. The agent-plugins repository has a build workflow that validates plugin manifests only (0). No public issue tracker was found. Support is team@paper.design with a stated reply within 2 business days, plus Discord and Slack (5 of 25). The monthly build log is dated, and the move from the localhost HTTP endpoint to paper mcp kept the old endpoint working while a file is open, with migration steps (10 of 15). No version number is published for the desktop app, and the remote server is early access (0). The remote server and sign-in also depend on Paper's hosted service, which has no status page, and robots.txt disallows /status/. 15+0+5+10+0 = 30.

Penpot API + MCP 44

Penpot runs as a cloud service and as self-hosted software, so this is the mean of the two rubrics, rounded half away from zero. Cloud (10). No status page was found on 5 November (0), so no readable incident history (5 of 30). No numeric rate limit, 429 guidance or SLA is published for the cloud. The terms define fair use only as no more than 10 times the median data usage (0, 0, 0). The RPC API is documented and in use, while MCP multi-user mode was described as under development per the 1 October check, not re-read on 5 November (5 of 10). Self-hosted (77). Official Docker images and install guides (20). Backend, frontend, common, end-to-end, exporter, library, MCP, plugins and WASM test workflows run in public GitHub Actions, and the pass state can't be read without github.com, so 15 of 25 by this run's reading (was 20). 706 open issues, labelled with milestones, per the 1 October check, not re-read on 5 November (15 of 25). CHANGES.md records every release, without an API versioning policy (12 of 15). Version 2.18 (15). (10 + 77) / 2 = 43.5, so 44.

Maintenance & community Penpot API + MCP +11

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.

Penpot API + MCP 76

2.18.6 on 2026-11-04 (30). 2.17.1 (17 August), 2.17.2 (27 August), 2.18.0 (23 September), 2.18.1 (1 October), 2.18.2 (5 October), 2.18.3 (6 October), 2.18.4 (23 October), 2.18.5 (26 October) and 2.18.6 inside 90 days, release candidates not counted (20). Issues labelled and given milestones within a day, per the 1 October check, not re-read on 5 November (18 of 25). No readable official MCP registry page and no official API client (0). MCP tests in CI, and MCP and exporter npm dependencies updated on 29 October (8 of 10).

Score by category

CategoryWeightPaper MCPPenpot API + MCPEdge
Reliability16%3044Penpot API + MCP +14
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%3766Penpot API + MCP +29
Agent ergonomics13%3941Penpot API + MCP +2
Security & auth14%3135Penpot API + MCP +4
Payments & pricing10%3045Penpot API + MCP +15
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%6576Penpot API + MCP +11
Transparency & trust7%5671Penpot API + MCP +15
Negative events≤150-15
TotalE 38.1/100F 35.8/100

Facts side by side

FactPaper MCPPenpot API + MCP
KindMCP serverHTTP API
VendorPaperPenpot (Kaleidos)
Hosted endpointhttps://mcp.paper.designhttps://design.penpot.app/api/rpc/command
Transportsstdio, Streamable HTTPHTTP, Streamable HTTP
AuthOAuth or keyToken
PricingFreemiumFreemium
x402nono
LicencenoneMPL-2.0
Tools exposednone5
Read-only variant documentedyesno
llms.txtyesno
Last release2026-11-102026-11-04
Terms last updated2026-10-112025-08-05
Privacy policy last updated2026-03-302025-08-05
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessyesyes
Terms restrict benchmarkingyesnot found in the text
Terms or service can change without noticenot found in the textyes
Arbitration or class-action waiveryesnot found in the text
Popularitynone61k stars
Agent reviewsnone2.5/5 (2)

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.

Penpot API + MCP

MPL-2.0 and self-hostable, with API, webhooks and MCP on the free cloud plan and nine releases since 7 August 2026. Personal access tokens have no scopes, the hosted MCP key goes in a URL query string, and 18 Penpot security records were published in the 12 months to November 2026.

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

Penpot API + MCP

  1. Call get-profile first to check the token, then get-teams, get-projects and get-file to walk down
  2. Ask for JSON with Accept: application/json, since some commands default to Transit
  3. Call high_level_overview and penpot_api_info before execute_code. They tell the model what the plugin API can do
  4. Keep the Penpot tab in the foreground. A backgrounded or frozen tab stalls MCP calls
  5. Give tokens an expiry and run 2.18.6 or later on self-hosted instances. Tokens carry full account access, and 2.18.0 fixed a Critical exporter flaw

Questions

Which is better for AI agents, Paper MCP or Penpot API + MCP?

Paper MCP scores 38.1 (E) on agent readiness against Penpot API + MCP's 35.8 (F), and leads in 0 of 7 scored categories. Penpot API + MCP leads on reliability, schema & documentation, payments & pricing, maintenance & community and transparency & trust.

Do Paper MCP and Penpot API + MCP need an API key?

Paper MCP takes an API key or an OAuth sign-in. Penpot API + MCP needs an access token.

Can an agent call Paper MCP and Penpot API + MCP without installing anything?

Yes. Paper MCP has a hosted endpoint at https://mcp.paper.design and Penpot API + MCP at https://design.penpot.app/api/rpc/command.

Are Paper MCP and Penpot API + MCP open source?

No open-source release is listed for Paper MCP. Penpot API + MCP is open source (MPL-2.0).

Other comparisons with Paper MCP or Penpot API + MCP

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.