Head to head · Design canvases · October 2026 research run

Melius vs Paper MCP

Melius scores 54.5 (C) on agent readiness against Paper MCP's 38.1 (E), and leads in 4 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

Melius C

Best for An agent producing batches of ad creative, product images or short videos on a shared canvas that people then review, with many models behind one key.

Ahead on

  • Reliability, 69 against 30
  • Schema & documentation, 70 against 37
  • Agent ergonomics, 51 against 39
  • Security & auth, 43 against 31

Watch for

API keys have no scopes. A key works with its creator's role in every team the creator belongs to

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 56

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

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.

Reliability Melius +39

Melius 69

Graded on the hosted REST API and MCP server. status.melius.com runs on incident.io with component history for Web app and MCP, though it has no API component (20). Its history listed no incidents from July to 8 October 2026, as far back as the page went. 9 October to 4 November is unread, and a partly unread window keeps its recorded award (30). No rate-limit numbers are published. The docs say only that no plan has a monthly request quota and that bursts can return 429 (0). 429s carry Retry-After and a retryAfterSeconds body field, and the docs give a bounded retry policy and tell clients to check canvas or run state after a timeout or 5xx on a write. There are no idempotency keys (12 of 15). No SLA found (0). The API and MCP server carry no beta label, but the CLI is at 0.16.2 and Cast and media-URL inputs are marked beta (7 of 10). Per the 8 October check, not re-read on 4 November, because the terms of 30 October 2026 bar automated access to melius.com and its subdomains.

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.

Schema & documentation Melius +33

Melius 70

Public OpenAPI 3.0.2 spec with 59 operations (25). llms.txt, llms-full.txt and a Markdown copy of every docs page (10). 58 of the 59 operations have a summary and no description. The MCP reference gives each of 75 tools one line, with ordering rules for get_guide, show_presence and canvas_plan_layout, and the tool definitions themselves need a signed-in client, so we didn't read them (8 of 20). Request bodies are typed with 336 enums, ranges, UUID formats and required fields, with 52 open additionalProperties objects (13 of 15). 401, 403 and 429 are declared on every operation and 400, 404 and 409 where they apply, but the spec has no examples and most error bodies are a bare message (9 of 15). The path is versioned at /api/v1 and the CLI states semantic versioning. No public changelog found (5 of 15). Per the 8 October check, not re-read on 4 November, because the terms of 30 October 2026 bar automated access to melius.com and its subdomains.

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.

Agent ergonomics Melius +12

Melius 51

The MCP reference lists 75 tools, in the over-30 band, with get_guide and get_docs loading guidance on demand and 18 Cast tools shown only to teams with access (10 of 25). Four list operations take limit and offset and three take search, canvas content can be narrowed to one node or to media summaries, and the CLI has --fields (14 of 20). REST errors carry statusCode, error and message, the CLI adds a code and a suggestion, and CANVAS_TOO_LARGE is documented as not worth retrying. A shortage of credits arrives as a plain 400 (14 of 20). No idempotency keys, and we couldn't read MCP annotations without an account. The docs do give safe-retry guidance (5 of 20). Auto model selection and defaults keep required fields few. There is no SDK library, only the CLI and generated code samples in six languages (8 of 15). Per the 8 October check, not re-read on 4 November, because the terms of 30 October 2026 bar automated access to melius.com and its subdomains.

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.

Security & auth Melius +12

Melius 43

API keys are revocable at once, can expire and are shown once, but have no scopes. A key works with its creator's access in every team that user belongs to, capped at the user's role. The MCP OAuth flow uses S256 PKCE and dynamic client registration, lists no scopes, and ties the connector key to one team (22 of 30). A key made by a viewer can only read, bulk_delete_node asks the user to confirm and a run can return a pending approval, but there is no read-only key and the setup guide tells users to select Always Allow for every tool (9 of 20). Canvas text, comments from collaborators and files fetched by url_to_canvas reach the model, and no prompt-injection guidance was found (2 of 15). Keys list a lastUsedAt time, connector keys are named after the client, and generation history is kept per member. No audit log is documented (7 of 15). No security.txt, disclosure policy or bug bounty found. A Vanta trust centre exists at trust.melius.com but needs JavaScript, so certifications are unchecked (3 of 20). Per the 8 October check, not re-read on 4 November, because the terms of 30 October 2026 bar automated access to melius.com and its subdomains.

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.

Maintenance & community Paper MCP +9

Melius 56

The newest dated release is the CLI, 0.16.2 on 10 September 2026 per the 8 October npm reading, 55 days before this check. The vendor's Homebrew tap, whose bot tracks npm hourly, has no version after 0.16.2, and no other dated source could be read (20). Versions 0.15.0 to 0.16.2, eight in all, fall between 7 August and 10 September by the tap's bump commits, which match the 19 versions since 10 July in the 8 October npm reading (20). Closed service with no public changelog or issue tracker. Support is by email at support@melius.com and a Discord server linked from the site (5 of 15). There is no SDK library, though the CLI is on npm and Homebrew (5 of 15). The CLI has three dependencies, needs Node.js 20 and is published from GitHub Actions through npm trusted publishing. Its source is not public (6 of 10).

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.

Score by category

CategoryWeightMeliusPaper MCPEdge
Reliability16%6930Melius +39
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%7037Melius +33
Agent ergonomics13%5139Melius +12
Security & auth14%4331Melius +12
Payments & pricing10%3030even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%5665Paper MCP +9
Transparency & trust7%5656even
Negative events≤1500
TotalC 54.5/100E 38.1/100

Facts side by side

FactMeliusPaper MCP
KindHTTP APIMCP server
VendorMelius AI, Inc.Paper
Hosted endpointhttps://api.melius.com/api/v1https://mcp.paper.design
TransportsHTTP, Streamable HTTPstdio, Streamable HTTP
AuthOAuth or keyOAuth or key
PricingFreemiumFreemium
x402nono
LicenceProprietary service under Melius's terms of service. The mel CLI on npm is MIT, with no public source repository foundnone
Tools exposed75none
Read-only variant documentednoyes
llms.txtyesyes
Last release2026-09-102026-11-10
Terms last updatedno date given2026-10-11
Privacy policy last updatedno date given2026-03-30
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 waiveryesyes
Popularity9 npm/wknone

How the scores have moved

Verdicts

Melius

One backend serves a 59-operation REST API with a public OpenAPI spec, a hosted MCP server with OAuth sign-in and a JSON-only CLI, and the status page showed no incidents from July to early October 2026. API keys carry no scopes and work with their creator's role, and no rate-limit numbers, changelog or per-model credit prices are published.

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.

Before you call either

Melius

  1. Generate by creating a node on a canvas, starting a run with POST /nodes/{nodeId}/runs, then polling GET /node-runs/{nodeRunId} until status is finished or failed
  2. Over MCP, call get_guide first, show_presence before node changes and canvas_plan_layout before bulk_create_nodes
  3. On 429 wait Retry-After seconds. After a timeout or 5xx on a write, read the canvas or run state before resubmitting, because there are no idempotency keys
  4. Read credit costs from GET /generation/models?category=image before a bulk run. A 400 can mean the team is out of credits
  5. Downloads arrive as a ZIP from a signed URL. Fetch that URL without the Authorization header

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

Questions

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

Melius scores 54.5 (C) on agent readiness against Paper MCP's 38.1 (E), and leads in 4 of 7 scored categories. Paper MCP leads on maintenance & community.

Do Melius and Paper MCP need an API key?

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

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

Yes. Melius has a hosted endpoint at https://api.melius.com/api/v1 and Paper MCP at https://mcp.paper.design.

Other comparisons with Melius or Paper 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.