# Astryx vs Paper MCP

> Astryx scores 71.7 (BB) to Paper MCP's 38.1 (E) for design components. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/astryx-vs-paper-mcp
- Markdown: https://www.anchorterminal.com/compare/astryx-vs-paper-mcp.md (~4,650 tokens)
- Slim: https://www.anchorterminal.com/compare/astryx-vs-paper-mcp.min.md (~1,080 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/astryx-vs-paper-mcp.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-18

Astryx scores 71.7 (BB) on agent readiness against Paper MCP's 38.1 (E), and leads in every scored category. Both do design components.

- Astryx: grade BB, 71.7/100, rank #260 of 1557. Markdown https://www.anchorterminal.com/tools/astryx.md · JSON https://www.anchorterminal.com/api/v1/tools/astryx.json
- Paper MCP: grade E, 38.1/100, rank #1404 of 1557. Markdown https://www.anchorterminal.com/tools/paper-mcp.md · JSON https://www.anchorterminal.com/api/v1/tools/paper-mcp.json
- Best design workspace and canvas APIs for AI agents: https://www.anchorterminal.com/best/design/index.md
- All 162 design comparisons: https://www.anchorterminal.com/compare/design/index.md

## Which one, for what

### Astryx (BB)

Good for: Coding agents building React 19 interfaces that want a component library they can query for props, templates and themes.

Ahead on:
- Reliability, 62 against 30
- Schema & documentation, 90 against 37
- Agent ergonomics, 65 against 39
- Security & auth, 61 against 31
- Payments & pricing, 90 against 30
- Maintenance & community, 75 against 65
- Transparency & trust, 64 against 56

Also in its favour:
- Agent-ready, a grade of BB or better
- No key needed to call it
- Open source

Watch for: Version 0.7.x and called a beta in the README and on the home page. Charts are published only under the `canary` tag

### Paper MCP (E)

Good 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.

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


## Why the edge

### Payments & pricing: Astryx +60

- Astryx (90): Free self-hosted software with nothing to buy, so 30 + 30 + 30. No payment protocol (0). Total 90.
- 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.

### Schema & documentation: Astryx +53

- Astryx (90): MCP reading. Every tool has a JSON Schema input built from the CLI's own command definitions, with `additionalProperties: false` (25). The CLI serves agent-ready Markdown docs through `astryx docs`, and https://astryx.atmeta.com/llms.txt tells agents to use the CLI instead of crawling the site (10). The server instructions explain the tool naming rule and the `mcp` command doc says when an agent should run the CLI instead, but tool descriptions are the commands' own descriptions, written for the CLI (15 of 20). Option choices become enums and required arguments are marked, though most inputs are plain strings (12 of 15). Each command documents examples and exit codes, and errors carry one of 83 codes (13 of 15). Tagged releases and per-package changelogs (15). Total 90.
- 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.

### Reliability: Astryx +32

- Astryx (62): Scored as a local package, since the owner runs it. Official npm packages with Node 22.13 or later and React 19 or later stated (20). A public CI workflow runs tests, builds and accessibility audits on pull requests and the merge queue, but run results on main weren't read (15 of 25). The repository had 348 open issues on 18 November 2026. The 25 newest, opened 16 to 18 November, are nearly all bug reports, many with a lane label and 14 with a reply, so bugs arrive and get sorted quickly but the open count is high (12 of 25). Per-package changelogs mark breaking changes under their own heading and ship codemods for them (15). Version 0.7.x, called a beta in the README and on the home page (0). Total 62.
- 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.

### Security & auth: Astryx +30

- Astryx (61): Local software with no credentials, so the middle band, as for other keyless local tools (20). `--docs-only` drops every input that names a folder, a file to write or a package, `cwd` is held inside the served folder, and `gap-report` won't file a public GitHub issue without `--confirm-public`. Other writes have no approval step (14 of 20). Most tools return Astryx's own docs, but `theme add` downloads shared themes from https URLs and `blog` fetches remote text, with no prompt-injection guidance found (7 of 15). `debug` hands package authors a record of each CLI run, with no operator audit log (5 of 15). SECURITY.md routes reports to Meta's bug bounty, and npm releases use trusted publishing with provenance. astryx.atmeta.com serves no security.txt (15 of 20). Total 61.
- 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.

### Agent ergonomics: Astryx +26

- Astryx (65): Read from source, not from a run. The local server lists 31 tools (5), with 10 back for `--docs-only`, a nine-tool read-only subset (15 of 25). `--limit` on search, build and discover, a domain filter on search, and `--detail` and `--dense` to size answers, but no paging (16 of 20). A failing command returns its JSON error with `isError`, and errors carry codes and suggested fixes (18 of 20). No readOnlyHint or destructiveHint annotations. Template, swizzle and theme writes refuse to overwrite without `--overwrite`, and `integration add` has `--dry-run` (8 of 20). Few required inputs, but JavaScript only (8 of 15). Total 65.
- 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.

### Maintenance & community: Astryx +10

- Astryx (75): v0.7.16 tagged on 13 November 2026, five days before this check, with commits on main on 18 November (30). Five or more releases in the last 90 days, including v0.7.10 on 6 November and v0.7.13 to v0.7.16 from 10 to 13 November (20). 348 open issues and 704 open pull requests on 18 November. Of the 25 newest issues, opened 16 to 18 November, 14 had a reply and many carried a lane label (15 of 25). No Astryx entry in the official MCP registry, searched for astryx and astryxdesign on 18 November (0 of 15). Dependabot, a pinned pnpm lockfile and CI workflows (10). Total 75.
- 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

| Category | Weight | Astryx | Paper MCP | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% | 62 | 30 | Astryx +32 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 90 | 37 | Astryx +53 |
| Agent ergonomics | 13% | 65 | 39 | Astryx +26 |
| Security & auth | 14% | 61 | 31 | Astryx +30 |
| Payments & pricing | 10% | 90 | 30 | Astryx +60 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 75 | 65 | Astryx +10 |
| Transparency & trust | 7% | 64 | 56 | Astryx +8 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **71.7 · BB** | **38.1 · E** | |

## Facts side by side

| Fact | Astryx | Paper MCP |
| --- | --- | --- |
| Kind | SDK + MCP | MCP server |
| Vendor | Meta | Paper |
| Hosted endpoint | `https://astryx.atmeta.com/mcp` | `https://mcp.paper.design` |
| Transports | stdio, Streamable HTTP | stdio, Streamable HTTP |
| Auth | None | OAuth or key |
| Pricing | Free | Freemium |
| x402 | no | no |
| Licence | MIT | none |
| Tools exposed | 31 | none |
| Read-only variant documented | yes | yes |
| llms.txt | yes | yes |
| Last release | 2026-11-13 | 2026-11-10 |
| Terms last updated | no document linked | 2026-10-11 |
| Privacy policy last updated | no document linked | 2026-03-30 |
| Customer content may train models | not read yet | not found in the text |
| Terms restrict automated access | not read yet | yes |
| Terms restrict benchmarking | not read yet | yes |
| Terms or service can change without notice | not read yet | not found in the text |
| Arbitration or class-action waiver | not read yet | yes |
| Popularity | 31k stars | none |

## How the scores have moved

### Astryx

- +4.0 on 18 November 2026 (B to BB): new evidence

### Paper MCP

- -0.1 on 18 November 2026: terms

## Verdicts

**Astryx.** Astryx gives a coding agent typed MCP tools to search components, read docs and build themes, with no account and an MIT licence, and Meta tagged four releases from 10 to 13 November 2026. It is a 0.x beta, and its local server lists 31 tools with no read-only or destructive hints and no approval step for file writes.

**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

### Astryx

1. Run `astryx` directly when you can run commands. Use `astryx mcp` only from a client that reaches tools through MCP
2. Use `astryx mcp --docs-only` or https://astryx.atmeta.com/mcp when you only need to look things up, since those tools can't write files
3. Pass `--limit` to search, build and discover, and `--detail` or `--dense`, to keep answers small
4. Before `theme add` from a URL, check the source, because a shared theme is downloaded and installed into the project
5. Read the `code` in a failed tool's JSON error and follow its suggested fix before retrying

### 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, Astryx or Paper MCP?

Astryx scores 71.7 (BB) on agent readiness against Paper MCP's 38.1 (E), and leads in every scored category.

### Can an agent call Astryx and Paper MCP without installing anything?

Yes. Astryx has a hosted endpoint at https://astryx.atmeta.com/mcp and Paper MCP at https://mcp.paper.design.

### Are Astryx and Paper MCP open source?

Astryx is open source (MIT). No open-source release is listed for Paper MCP.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/astryx-vs-paper-mcp.json, and with the fewest tokens: https://www.anchorterminal.com/compare/astryx-vs-paper-mcp.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "astryx", "b": "paper-mcp"}`. From a terminal: `anchor compare astryx paper-mcp`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/astryx.json and https://www.anchorterminal.com/api/v1/tools/paper-mcp.json

## Other comparisons with Astryx or Paper MCP

- [Figma API + MCP vs Paper MCP](https://www.anchorterminal.com/compare/figma-mcp-vs-paper-mcp.md)
- [Framelink MCP for Figma vs Paper MCP](https://www.anchorterminal.com/compare/framelink-figma-mcp-vs-paper-mcp.md)
- [Framer Server API vs Paper MCP](https://www.anchorterminal.com/compare/framer-vs-paper-mcp.md)
- [Kite vs Paper MCP](https://www.anchorterminal.com/compare/kite-new-vs-paper-mcp.md)
- [Miro API + MCP vs Paper MCP](https://www.anchorterminal.com/compare/miro-vs-paper-mcp.md)
- [Paper MCP vs Zeplin](https://www.anchorterminal.com/compare/paper-mcp-vs-zeplin.md)
- [Astryx vs Figma API + MCP](https://www.anchorterminal.com/compare/astryx-vs-figma-mcp.md)
- [Astryx vs Framelink MCP for Figma](https://www.anchorterminal.com/compare/astryx-vs-framelink-figma-mcp.md)
- [Astryx vs Framer Server API](https://www.anchorterminal.com/compare/astryx-vs-framer.md)
- [Astryx vs Impeccable](https://www.anchorterminal.com/compare/astryx-vs-impeccable.md)
- [Astryx vs Kite](https://www.anchorterminal.com/compare/astryx-vs-kite-new.md)
- [Astryx vs Magic Patterns](https://www.anchorterminal.com/compare/astryx-vs-magic-patterns.md)
- [Astryx vs pen.dev](https://www.anchorterminal.com/compare/astryx-vs-pen-dev.md)
- [Astryx vs Penpot API + MCP](https://www.anchorterminal.com/compare/astryx-vs-penpot.md)
- [Astryx vs Sketch](https://www.anchorterminal.com/compare/astryx-vs-sketch.md)
- [Astryx vs Subframe](https://www.anchorterminal.com/compare/astryx-vs-subframe.md)
- [Astryx vs UXKIN](https://www.anchorterminal.com/compare/astryx-vs-uxkin-agent.md)
- [Astryx vs Zeplin](https://www.anchorterminal.com/compare/astryx-vs-zeplin.md)
- [Paper MCP vs UXKIN](https://www.anchorterminal.com/compare/paper-mcp-vs-uxkin-agent.md)
- [Astryx vs UX Pilot MCP server](https://www.anchorterminal.com/compare/astryx-vs-ux-pilot-mcp.md)
- [Impeccable vs Paper MCP](https://www.anchorterminal.com/compare/impeccable-vs-paper-mcp.md)
- [Magic Patterns vs Paper MCP](https://www.anchorterminal.com/compare/magic-patterns-vs-paper-mcp.md)
- [Melius vs Paper MCP](https://www.anchorterminal.com/compare/melius-vs-paper-mcp.md)
- [Paper MCP vs pen.dev](https://www.anchorterminal.com/compare/paper-mcp-vs-pen-dev.md)
- [Paper MCP vs Penpot API + MCP](https://www.anchorterminal.com/compare/paper-mcp-vs-penpot.md)
- [Paper MCP vs Sketch](https://www.anchorterminal.com/compare/paper-mcp-vs-sketch.md)
- [Paper MCP vs Subframe](https://www.anchorterminal.com/compare/paper-mcp-vs-subframe.md)
- [Paper MCP vs UX Pilot MCP server](https://www.anchorterminal.com/compare/paper-mcp-vs-ux-pilot-mcp.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp
