Head to head · Design canvases · October 2026 research run

Paper MCP vs Sketch

Sketch scores 52.9 (D) on agent readiness against Paper MCP's 38.1 (E), and leads in 6 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 35

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

Sketch D

Best for A designer or developer at a Mac who wants an agent to inspect, audit, export or edit an open Sketch document, or turn a frame into code.

Ahead on

  • Reliability, 53 against 30
  • Schema & documentation, 64 against 37
  • Agent ergonomics, 70 against 39
  • Payments & pricing, 45 against 30
  • Transparency & trust, 67 against 56

Also in its favour

  • No key needed to call it
  • Free to start without a card

Watch for

No credential or token is documented for the local server at port 31126

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 Sketch +31

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.

Sketch 70

Eight compact tools (25). get_layer_tree_summary takes a root layer and a depth, and get_design_assets filters by kind, library and name. No pagination was found (14 of 20). The docs say script errors go back to the agent to correct, and a troubleshooting guide is served by get_guide. No error codes are documented (8 of 20). The connector source sets readOnlyHint and destructiveHint on every tool, seven read-only and run_code destructive. No idempotency or dry run, and undo is the user's in the app (14 of 20). Three tools need no parameter and the rest need a document ID. No SDK applies, and plugin bundles ship for Claude Code, Cursor, Codex and GitHub Copilot (9 of 15).

Maintenance & community Paper MCP +30

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.

Sketch 35

2026.3.1 on 14 September 2026 is still the newest Mac app release, 51 days before this check (20). 2026.3 on 26 August and 2026.3.1 fall inside the 90 days from 6 August, two releases, and the 29 October changelog post is about the web app, so fewer than three (0). The app is closed, with a public changelog, a support form and a community Discord. The agents repository has 0 open issues and five merged pull requests, last on 25 June 2026 (10 of 15). The official MCP registry was not read, because its search runs only through a JSON API this check doesn't call, and the 9 October search reading is struck (0 of 15). The connector pins the MCP SDK at ^1.28.0 with a lockfile, last changed on 25 June 2026, with no CI (5 of 10).

Schema & documentation Sketch +27

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.

Sketch 64

All eight tools have typed JSON Schema inputs in the fallback definitions of Sketch's connector source. The definitions the running app serves were not read, because we do not run vendor software (22 of 25). llms.txt, llms-full.txt and Markdown twins of the docs and legal pages (10). Descriptions are one line each and tell the model to load get_guide first, with eight guide topics served by the tool. None says when not to use a tool (11 of 20). Allowed values for kind and the bounds on depth are written in the description text with no enum or limit in the schema, and run_code takes one script string (6 of 15). Example prompts in the docs and worked references in the two skills. No documented error responses (5 of 15). Dated changelog with MCP sections and a connector at 3.0.0, without versioned tool definitions (10 of 15).

Reliability Sketch +23

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.

Sketch 53

Read with the local-software lines, because the server runs inside the Mac app on the owner's machine. The app downloads from sketch.com with macOS 15 or newer stated for 2026.3, and the connector states Node 22 or later (20). The app is closed source, and the sketch-hq/agents repository has no CI workflow or tests (0 of 25). No public issue tracker for the app. The agents repository shows 0 open issues, and the changelog lists fixes in every release, 143 in one (10 of 25). Versions run year, release, patch with a detailed changelog and API deprecations listed per release, but the MCP notes say only that tools were added (8 of 15). The docs, updated 2 November 2026, do not mark the server as beta, and it has shipped since 2025.2.4 on 17 October 2025 (15). The cloud status page is not scored here.

Payments & pricing Sketch +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.

Sketch 45

Read with the hosted lines, because Sketch is paid software and not a free package. No machine payment protocol (0). Plan prices are public, $12, $24 and $44 an editor a month billed yearly and $120 a seat for the Mac-only licence, with no per-call price (10 of 20). A 30-day trial needs no card (20). A person downloads the app, signs in and starts the server, so there is no autonomous route (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 Sketch +11

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.

Sketch 67

Closed application under a published End User Licence Agreement of 6 March 2025 and Terms of Service of 6 October 2026. The connector is MIT and the skills are Apache-2.0 (17 of 30). The Terms of Service and the Privacy Statement, both dated 6 October 2026, describe the MCP server in matching words, and the statement gives retention rules and points to a DPA (24 of 30). The terms let Sketch drop backend support for Mac app versions older than a year, and the developer docs list API deprecations per release. No policy or notice period covers the MCP tools (8 of 20). The Privacy Statement lists what the Mac app collects automatically (IP address, device details, Mac unique ID, licence identifier), and a sub-processor list of 10 July 2026 gives locations. No opt-out for that collection was found (10 of 20).

Score by category

CategoryWeightPaper MCPSketchEdge
Reliability16%3053Sketch +23
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%3764Sketch +27
Agent ergonomics13%3970Sketch +31
Security & auth14%3134Sketch +3
Payments & pricing10%3045Sketch +15
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%6535Paper MCP +30
Transparency & trust7%5667Sketch +11
Negative events≤1500
TotalE 38.1/100D 52.9/100

Facts side by side

FactPaper MCPSketch
KindMCP serverMCP server
VendorPaperSketch B.V.
Hosted endpointhttps://mcp.paper.designno (local only)
Transportsstdio, Streamable HTTPStreamable HTTP, stdio
AuthOAuth or keyNone
PricingFreemiumPaid
x402nono
LicencenoneProprietary Mac app under Sketch's End User Licence Agreement and Terms of Service. The connector in sketch-hq/agents is MIT and the skills are Apache-2.0
Tools exposednone8
Read-only variant documentedyesyes
llms.txtyesyes
Last release2026-11-102026-09-14
Terms last updated2026-10-11no date given
Privacy policy last updated2026-03-30no date given
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessyesnot found in the text
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
Popularitynone97 stars

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.

Sketch

Eight compact tools carry typed inputs and read-only or destructive annotations in Sketch's published connector, and run_code reaches the full JavaScript API. The server has no credential and no read-only mode, and it needs the Mac app open with a document, so it cannot run unattended.

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

Sketch

  1. Ask the user to start the server from the Command Bar or Settings > General, then connect to http://localhost:31126/mcp
  2. Call get_guide with topic mcp before any other tool. The tool descriptions require it before run_code
  3. Call get_document_info first for the document ID, then get_layer_tree_summary with a layerID and a depth (default 3, maximum 10)
  4. Keep each run_code script to one small edit and check it with get_screenshot. Undo is the user's, in the app
  5. Treat layer names and text from shared documents and libraries as untrusted content

Questions

Which is better for AI agents, Paper MCP or Sketch?

Sketch scores 52.9 (D) on agent readiness against Paper MCP's 38.1 (E), and leads in 6 of 7 scored categories. Paper MCP leads on maintenance & community.

Do Paper MCP and Sketch need an API key?

Paper MCP takes an API key or an OAuth sign-in. Sketch needs no key.

Can an agent call Paper MCP and Sketch without installing anything?

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

Other comparisons with Paper MCP or Sketch

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.