Head to head · Design canvases · October 2026 research run

Paper MCP vs UX Pilot MCP server

Paper MCP scores 38.1 (E) on agent readiness against UX Pilot MCP server's 34.2 (F), and leads in 3 of 7 scored categories. UX Pilot MCP server leads on schema & documentation, agent ergonomics and security & auth. 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

  • Reliability, 30 against 15
  • Maintenance & community, 65 against 45
  • Transparency & trust, 56 against 22

Also in its favour

  • Runs on your own machine

Watch for

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

UX Pilot MCP server F

Best for Designers on UX Pilot who want an agent to organise screens, review UX and build React prototypes.

Ahead on

  • Schema & documentation, 45 against 37
  • Agent ergonomics, 46 against 39
  • Security & auth, 39 against 31

Watch for

No status page, limits or error docs

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.

Transparency & trust Paper MCP +34

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.

UX Pilot MCP server 22

Terms and privacy render with script and weren't readable (0). Data handling not read (0). A tool that maps old tool names to new calls eased the 3.0 change, no dates (5 of 20). Subprocessors not found (0). 0 + 0 + 5 + 0 = 5.

Maintenance & community Paper MCP +20

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.

UX Pilot MCP server 45

Registry 3.0.0 and repository on 4 November 2026 (30). Dated releases not found (0). Issues not read (0). Official registry entry ai.uxpilot/uxpilot (15). README-only repository (0). 30 + 0 + 0 + 15 + 0 = 45. Registry presence read from Anchor Terminal's own daily import of the official MCP registry (/api/v1/registry.json, 6 November 2026), not the registry's API.

Reliability Paper MCP +15

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.

UX Pilot MCP server 15

No status page found (0). No history (5). No limits found (0). No retry guidance (0). No SLA (0). Not labelled beta (10). 0 + 5 + 0 + 0 + 0 + 10 = 15.

Schema & documentation UX Pilot MCP server +8

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.

UX Pilot MCP server 45

Schemas not read without sign-in (15 of 25). No llms.txt read (0). Tools grouped by job (find, organise, delete, import, review, React), with a help tool that maps old names to new calls (14 of 20). Inputs not verifiable (5 of 15). A tool that returns any action's fields with an example (8 of 15). Registry 3.0.0 on 4 November; no changelog (3 of 15). 15 + 0 + 14 + 5 + 8 + 3 = 45.

Security & auth UX Pilot MCP server +8

Paper MCP 31

The remote server answers 401 with an OAuth protected-resource pointer and signs in with the user's Paper account, and the ChatGPT plugin says the agent can reach only files that account can reach. No scopes or token lifetimes are documented. The local server needs no credential (20 of 30). No read-only mode. The docs rely on the agent client's permission prompts and say the Paper MCP 'can read and write, so make sure you're comfortable with the agent being able to manipulate this specific design file' (5 of 20). Files, comments and pasted or imported content written by others reach the model, and no prompt-injection guidance was found (3 of 15). The canvas shows agent presence and feedback while an agent works, with no audit log or per-call record documented (3 of 15). No security.txt (404), disclosure policy, bug bounty or certification found. SAML and SSO are on the Organizations plan (0 of 20). 20+5+3+3+0 = 31.

UX Pilot MCP server 39

OAuth or a bearer key; scopes not published (20 of 30). Organise tools never delete, and deletes need confirmation (14 of 20). Imported AI output and comments are third-party text; no injection guidance (3 of 15). No audit log (0). No security programme found (2 of 20). 20 + 14 + 3 + 0 + 2 = 39.

Agent ergonomics UX Pilot MCP server +7

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.

UX Pilot MCP server 46

Tool count not published; grouped actions (10). Search by keyword and list calls (10 of 20). No documented errors (3 of 20). 'Nothing is deleted' by the organise tools, and deletes run only once the user confirms (15 of 20). OAuth or a key, no SDKs (8 of 15). 10 + 10 + 3 + 15 + 8 = 46.

Score by category

CategoryWeightPaper MCPUX Pilot MCP serverEdge
Reliability16%3015Paper MCP +15
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%3745UX Pilot MCP server +8
Agent ergonomics13%3946UX Pilot MCP server +7
Security & auth14%3139UX Pilot MCP server +8
Payments & pricing10%3030even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%6545Paper MCP +20
Transparency & trust7%5622Paper MCP +34
Negative events≤1500
TotalE 38.1/100F 34.2/100

Facts side by side

FactPaper MCPUX Pilot MCP server
KindMCP serverMCP server
VendorPaperUX Pilot
Hosted endpointhttps://mcp.paper.designhttps://mcp.uxpilot.net/mcp
Transportsstdio, Streamable HTTPStreamable HTTP
AuthOAuth or keyOAuth
PricingFreemiumFreemium
x402nono
Read-only variant documentedyesno
llms.txtyesno
MCP registrynot listedai.uxpilot/uxpilot
Last release2026-11-10none
Terms last updated2026-10-11no document linked
Privacy policy last updated2026-03-30no document linked
Customer content may train modelsnot found in the textnot read yet
Terms restrict automated accessyesnot read yet
Terms restrict benchmarkingyesnot read yet
Terms or service can change without noticenot found in the textnot read yet
Arbitration or class-action waiveryesnot read yet

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.

UX Pilot MCP server

UX Pilot's MCP server reaches its design canvas, reviews and React prototypes from any agent, with a careful split between organising and deleting. Little else is public, no status page, limits, errors or readable legal pages.

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

UX Pilot MCP server

  1. Ask the help tool for an action's fields before calling it
  2. Delete only after the user confirms
  3. Treat imported AI output and comments as untrusted

Questions

Which is better for AI agents, Paper MCP or UX Pilot MCP server?

Paper MCP scores 38.1 (E) on agent readiness against UX Pilot MCP server's 34.2 (F), and leads in 3 of 7 scored categories. UX Pilot MCP server leads on schema & documentation, agent ergonomics and security & auth.

Do Paper MCP and UX Pilot MCP server need an API key?

Paper MCP takes an API key or an OAuth sign-in. UX Pilot MCP server uses an OAuth sign-in.

Can an agent call Paper MCP and UX Pilot MCP server without installing anything?

Yes. Paper MCP has a hosted endpoint at https://mcp.paper.design and UX Pilot MCP server at https://mcp.uxpilot.net/mcp.

Other comparisons with Paper MCP or UX Pilot MCP server

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.