{ "data": { "category": { "area": "design-diagrams", "capabilities": [ "design.files", "design.components", "design.canvas", "design.comments", "design.code" ], "description": "Design tools and shared canvases an agent can read from and write to. Files, frames, components, variables, boards and comments. Compared on what the API can change as well as read, design-to-code support, MCP servers and how access is scoped.", "indexed": [ { "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/scalably-figma-mcp.json", "kind": "mcp", "name": "Figma MCP", "slug": "scalably-figma-mcp", "url": "https://www.anchorterminal.com/tools/scalably-figma-mcp" }, { "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/shippp-mcp.json", "kind": "mcp", "name": "shippp.ai MCP server", "slug": "shippp-mcp", "url": "https://www.anchorterminal.com/tools/shippp-mcp" } ], "indexedCount": 2, "json": "https://www.anchorterminal.com/categories/design.json", "name": "Design workspaces \u0026 canvases", "slug": "design", "test": "", "title": "Design workspace and canvas APIs for AI agents", "toolCount": 10, "tools": [ "figma-mcp", "miro", "lucid", "melius", "sketch", "framer", "pen-dev", "zeplin", "penpot", "subframe" ], "url": "https://www.anchorterminal.com/categories/design" }, "faq": [ { "answer": "Figma API + MCP has the highest benchmark score of the 10 ranked design workspace and canvas APIs, 66 (B). Miro API + MCP is second with 65 (B).", "question": "What are the highest-rated design workspace and canvas APIs for AI agents?" }, { "answer": "0 of the 10 ranked here grade BB or better, the bar for agent-ready on the Anchor benchmark.", "question": "How many design workspace and canvas APIs are agent-ready?" }, { "answer": "None of the ranked listings here accepts x402 for its main call yet.", "question": "Which design workspace and canvas APIs accept x402 payments?" }, { "answer": "By the Anchor benchmark score out of 100, a weighted mean of the scored categories minus deductions for negative events, from public evidence re-checked as vendors change. Listings cannot pay for a place. The latest assessment behind this page is from 9 October 2026.", "question": "How is this list ranked?" } ], "howToChoose": [ { "label": "Read and write coverage", "detail": "Check which objects the API can change as well as read, since an agent that can only read frames cannot apply the fixes it finds." }, { "label": "Auth scopes and access", "detail": "Check that access scopes can be limited to single files, because a token that opens a whole team gives an agent more reach than the task needs." }, { "label": "Design-to-code and export formats", "detail": "Check which export formats and design-to-code outputs are available, since an agent that turns a frame into code needs output it can parse without a manual step." }, { "label": "MCP tools and rate limits", "detail": "List the MCP tools and their rate limits, because an agent that reads a canvas one frame at a time can hit a limit before the design is finished." } ], "picks": [ { "also": { "name": "Miro API + MCP", "slug": "miro", "why": "B, 65/100" }, "name": "Figma API + MCP", "need": "Highest score overall", "slug": "figma-mcp", "why": "B, 66/100 on the benchmark" }, { "name": "Miro API + MCP", "need": "Reliability", "slug": "miro", "why": "73/100 on reliability, against 59 for the overall leader" }, { "name": "Sketch", "need": "Agent ergonomics", "slug": "sketch", "why": "70/100 on agent ergonomics, against 60 for the overall leader" }, { "name": "Lucid API + MCP", "need": "Security \u0026 auth", "slug": "lucid", "why": "80/100 on security \u0026 auth, against 74 for the overall leader" }, { "name": "Miro API + MCP", "need": "Transparency \u0026 trust", "slug": "miro", "why": "76/100 on transparency \u0026 trust, against 73 for the overall leader" }, { "name": "Penpot API + MCP", "need": "Self-hosting under an open licence", "slug": "penpot", "why": "self-hosted, MPL-2 licence" } ], "ranked": 10, "shortlist": [ { "bestFor": "Design-to-code agents and teams already paying for Dev or Full seats.", "grade": "B", "name": "Figma API + MCP", "position": 1, "price": "$16 / seat-mo", "score": 66, "slug": "figma-mcp", "strengths": [ "OpenAPI spec, TypeScript types and an llms.txt index for the REST API", "OAuth scopes per resource, plus plan access tokens with allowlists and expiry", "MCP design context, screenshots and Code Connect for design-to-code work, with canvas writes on the remote server" ], "url": "https://www.anchorterminal.com/tools/figma-mcp", "verdict": "OpenAPI spec, TypeScript types and an llms.txt index for the REST API. View and Collab seats get 6 MCP calls a month on paid plans.", "weaknesses": [ "View and Collab seats get 6 MCP calls a month on paid plans", "MCP tools were unavailable for about 4 hours on 26 August 2026", "Only clients in Figma's MCP catalogue can connect" ], "where": "hosted", "x402": "no" }, { "bestFor": "Agents that draw diagrams, maps and planning boards people will keep editing.", "grade": "B", "name": "Miro API + MCP", "position": 2, "price": "$8 / seat-mo", "score": 65, "slug": "miro", "strengths": [ "REST creates shapes, connectors and frames, so flowcharts and architecture sketches can be drawn directly", "Hosted MCP server with OAuth 2.1 on every plan including Free, and no delete tool in its 18", "Published REST credit limits and MCP daily caps per plan" ], "url": "https://www.anchorterminal.com/tools/miro", "verdict": "REST creates shapes, connectors and frames, so flowcharts and architecture sketches can be drawn directly. Legacy MCP board tools were removed nine days after the deprecation notice.", "weaknesses": [ "Legacy MCP board tools were removed nine days after the deprecation notice", "No prompt-injection guidance for board content written by collaborators", "OAuth scopes are coarse (`boards:read`, `boards:write`)" ], "where": "hosted", "x402": "no" }, { "bestFor": "Organisations already on Lucid that want an agent to create or update diagrams inside governed workspaces, with read-only scopes and audit logs.", "grade": "C", "name": "Lucid API + MCP", "position": 3, "price": "$9 / seat-mo", "score": 60.6, "slug": "lucid", "strengths": [ "OAuth 2.0 scopes with `:readonly` variants, and audit log endpoints in the REST API", "Mermaid in through REST, PlantUML sequence diagrams through MCP, both editable afterwards", "Per-operation rate limits in each reference page's OpenAPI fragment, such as 60 a minute on Create Mermaid Diagram" ], "url": "https://www.anchorterminal.com/tools/lucid", "verdict": "OAuth 2.0 scopes with `:readonly` variants, and audit log endpoints in the REST API. No public changelog for the API or the MCP server.", "weaknesses": [ "No public changelog for the API or the MCP server", "The status page doesn't monitor the API or the MCP server", "No single OpenAPI file and no official REST SDK" ], "where": "hosted", "x402": "no" }, { "bestFor": "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.", "grade": "C", "name": "Melius", "position": 4, "price": "$20 / mo", "score": 54.1, "slug": "melius", "strengths": [ "Public OpenAPI 3.0.2 spec with 59 operations, plus llms.txt, llms-full.txt and a Markdown copy of every docs page", "Hosted MCP server with OAuth sign-in (PKCE, dynamic client registration) or a bearer API key, tied to one team chosen at authorisation", "429 responses carry `Retry-After` and `retryAfterSeconds`, and the docs give a bounded retry policy" ], "url": "https://www.anchorterminal.com/tools/melius", "verdict": "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 shows no incidents since July 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.", "weaknesses": [ "API keys have no scopes. A key works with its creator's role in every team the creator belongs to", "No rate-limit numbers, SLA, public changelog or API deprecation policy found in the reviewed documentation", "The MCP reference lists 75 tools, and the setup guide tells users to select Always Allow for all of them" ], "where": "hosted", "x402": "no" }, { "bestFor": "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.", "grade": "D", "name": "Sketch", "position": 5, "price": "$12 / seat-mo", "score": 53.5, "slug": "sketch", "strengths": [ "Eight tools, seven marked read-only and `run_code` marked destructive in the connector source", "`run_code` runs scripts against the documented Sketch JavaScript API, so an agent can create, edit and export layers", "The server is off by default and listens on localhost only, per the docs" ], "url": "https://www.anchorterminal.com/tools/sketch", "verdict": "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.", "weaknesses": [ "No credential or token is documented for the local server at port 31126", "No read-only mode. `run_code` is always listed, and approval depends on the connected client", "Needs the Mac app running with a document open. No hosted or headless route was found" ], "where": "local", "x402": "no" }, { "bestFor": "Coding agents that build or update Framer sites, CMS content and code components and can run Node.", "grade": "D", "name": "Framer Server API", "position": 6, "price": "$10 / mo", "score": 52.6, "slug": "framer", "strengths": [ "Same surface as the Plugin API, so canvas nodes, components, code files and CMS are writable", "`@framer/agent` puts every agent change on a branch and limits it to the projects you connect", "Publish makes a preview deployment that a separate `deploy` promotes" ], "url": "https://www.anchorterminal.com/tools/framer", "verdict": "Same surface as the Plugin API, so canvas nodes, components, code files and CMS are writable. No REST endpoints and no official MCP server. You need Node 22 and the `framer-api` package.", "weaknesses": [ "No REST endpoints and no official MCP server. You need Node 22 and the `framer-api` package", "Open beta with no published rate limits, price or SLA", "Not transactional, so failures can leave partial edits" ], "where": "local", "x402": "no" }, { "bestFor": "A coding agent that designs screens beside the code and keeps them in Git, including in CI.", "grade": "D", "name": "pen.dev", "position": 7, "price": "$16 / seat-mo", "score": 47.6, "slug": "pen-dev", "strengths": [ "Headless CLI (`@pen.dev/cli`) runs the same editor engine as the desktop app and exports PNG, JPEG, WEBP, PDF and HTML", "Four standard MCP tools with typed inputs and readOnlyHint and destructiveHint annotations, plus two conditional tools", "The `.pen` format is JSON with a published TypeScript schema, so designs sit in Git beside code" ], "url": "https://www.anchorterminal.com/tools/pen-dev", "verdict": "An agent can create, edit and export `.pen` designs without a GUI through the `pen` CLI, with four compact MCP tools that carry annotations and a documented JSON format. The software is closed and needs a pen.dev account. No changelog, status page or security contact was found, and 14 public issue reports had no reply on 8 October 2026.", "weaknesses": [ "No changelog. The three desktop releases on GitHub have empty notes, and the format docs reserve the right to make breaking changes", "14 issues opened between 28 July and 6 October 2026 in highagency/pen-desktop-releases had no comment or closure on 8 October", "No status page, security.txt, disclosure policy, bug bounty or certification was found" ], "where": "local", "x402": "no" }, { "bestFor": "Teams that already publish designs to Zeplin and want an agent to read screens, components, tokens and notes, or turn a screen into code through the MCP server.", "grade": "D", "name": "Zeplin", "position": 8, "price": "$13.75 / mo", "score": 47.5, "slug": "zeplin", "strengths": [ "123 documented operations, each with an OpenAPI 3.0.2 definition in a Markdown twin, indexed by `llms.txt`", "Rate limit stated as 200 requests a minute per user, with `Zeplin-RateLimit-Limit`, `-Remaining` and `-Reset` response headers", "OAuth 2.0 authorisation code grant with PKCE, one-hour access tokens and single-use refresh tokens" ], "url": "https://www.anchorterminal.com/tools/zeplin", "verdict": "The API documents 123 operations with typed parameters, a 200-requests-a-minute limit and OAuth with PKCE, and every plan includes it. Tokens carry no scopes, no status page was found on the pages read, and the API changelog's last entry is dated 11 May 2021.", "weaknesses": [ "OAuth tokens and personal access tokens carry no scopes. The OpenAPI security scheme lists none", "No status page is linked from the site, docs or help centre pages read", "The API changelog's last entry is 11 May 2021, though the reference has since gained variables, flow boards and annotations" ], "where": "local", "x402": "no" }, { "bestFor": "Teams that want design files on their own servers and an agent working alongside a person in the editor.", "grade": "E", "name": "Penpot API + MCP", "position": 9, "price": "$7 / seat-mo", "score": 43.5, "slug": "penpot", "strengths": [ "MPL-2.0 and self-hostable, with API, webhooks and MCP on the free cloud plan", "MCP `execute_code` reaches the whole plugin API, so an agent can create, move, restyle and delete shapes", "OpenAPI description served by every instance" ], "url": "https://www.anchorterminal.com/tools/penpot", "verdict": "MPL-2.0 and self-hostable, with API, webhooks and MCP on the free cloud plan. Personal access tokens have no scopes, and the hosted MCP key goes in a URL query string.", "weaknesses": [ "Personal access tokens have no scopes, and the hosted MCP key goes in a URL query string", "No annotations on MCP tools and no read-only mode", "Four advisories in 2026, including MCP REPL remote code execution" ], "where": "hosted", "x402": "no" }, { "bestFor": "A coding agent working beside a team that designs React and Tailwind interfaces in Subframe and wants the design as code, with a read-only route for review.", "grade": "E", "name": "Subframe", "position": 10, "price": "$20 / seat-mo", "score": 39.7, "slug": "subframe", "strengths": [ "Hosted MCP server at `https://mcp.subframe.com/mcp` with OAuth, dynamic client registration and PKCE, so no key is pasted into a config file", "Viewer accounts get a read-only MCP server and read-only CLI access, and Viewer seats are free on every plan", "Write tools cover pages, components, snippets, design documents, themes, icons and fonts, and page reads return generated React and Tailwind code" ], "url": "https://www.anchorterminal.com/tools/subframe", "verdict": "An agent can read and change pages, components, snippets and themes in a Subframe project through a hosted MCP server with OAuth, and Viewer accounts get a read-only server. The server lists 46 tools, and no status page, rate limits, changelog or security contact were found. Three tools were renamed in September 2026 with no notice found.", "weaknesses": [ "46 tools are documented with no toolsets, and the vendor's `design` skill that explains them is about 55 KB of text", "No status page, published rate limit, SLA or changelog was found, and the terms disclaim uninterrupted service", "`list_flows`, `get_flow_info` and `delete_flow` became `list_canvases`, `get_canvas_info` and `delete_canvas` in September 2026 with no notice found" ], "where": "hosted", "x402": "no" } ], "updated": "2026-10-09" }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/best/design/", "json": "https://www.anchorterminal.com/best/design/index.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/best/design/index.md", "slim": "https://www.anchorterminal.com/best/design/index.min.md" }, "markdown": "All 10 ranked design workspace and canvas APIs on the Anchor benchmark, with a pick for each need and where each one falls short. Scores come from public evidence, re-checked as vendors change.\n\n- Ranked: 10 · agent-ready (BB or better): 0 · accept x402: 0 · hosted endpoints: 6\n- Full ranked table: https://www.anchorterminal.com/categories/design.md\n- Head-to-head comparisons: https://www.anchorterminal.com/compare/design/index.md (49)\n- Methodology: https://www.anchorterminal.com/benchmark/index.md\n\n## The shortlist\n\n| # | Tool | Grade | Score | Best for | Price | Where |\n| --- | --- | --- | --- | --- | --- | --- |\n| 1 | [Figma API + MCP](https://www.anchorterminal.com/tools/figma-mcp.md) | B | 66 | Design-to-code agents and teams already paying for Dev or Full seats. | $16 / seat-mo | hosted |\n| 2 | [Miro API + MCP](https://www.anchorterminal.com/tools/miro.md) | B | 65 | Agents that draw diagrams, maps and planning boards people will keep editing. | $8 / seat-mo | hosted |\n| 3 | [Lucid API + MCP](https://www.anchorterminal.com/tools/lucid.md) | C | 60.6 | Organisations already on Lucid that want an agent to create or update diagrams inside governed workspaces, with read-only scopes and audit logs. | $9 / seat-mo | hosted |\n| 4 | [Melius](https://www.anchorterminal.com/tools/melius.md) | C | 54.1 | 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. | $20 / mo | hosted |\n| 5 | [Sketch](https://www.anchorterminal.com/tools/sketch.md) | D | 53.5 | 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. | $12 / seat-mo | local |\n| 6 | [Framer Server API](https://www.anchorterminal.com/tools/framer.md) | D | 52.6 | Coding agents that build or update Framer sites, CMS content and code components and can run Node. | $10 / mo | local |\n| 7 | [pen.dev](https://www.anchorterminal.com/tools/pen-dev.md) | D | 47.6 | A coding agent that designs screens beside the code and keeps them in Git, including in CI. | $16 / seat-mo | local |\n| 8 | [Zeplin](https://www.anchorterminal.com/tools/zeplin.md) | D | 47.5 | Teams that already publish designs to Zeplin and want an agent to read screens, components, tokens and notes, or turn a screen into code through the MCP server. | $13.75 / mo | local |\n| 9 | [Penpot API + MCP](https://www.anchorterminal.com/tools/penpot.md) | E | 43.5 | Teams that want design files on their own servers and an agent working alongside a person in the editor. | $7 / seat-mo | hosted |\n| 10 | [Subframe](https://www.anchorterminal.com/tools/subframe.md) | E | 39.7 | A coding agent working beside a team that designs React and Tailwind interfaces in Subframe and wants the design as code, with a read-only route for review. | $20 / seat-mo | hosted |\n\n## Picks by need\n\n- Highest score overall: [Figma API + MCP](https://www.anchorterminal.com/tools/figma-mcp.md), B, 66/100 on the benchmark. Also [Miro API + MCP](https://www.anchorterminal.com/tools/miro.md), B, 65/100.\n- Reliability: [Miro API + MCP](https://www.anchorterminal.com/tools/miro.md), 73/100 on reliability, against 59 for the overall leader.\n- Agent ergonomics: [Sketch](https://www.anchorterminal.com/tools/sketch.md), 70/100 on agent ergonomics, against 60 for the overall leader.\n- Security \u0026 auth: [Lucid API + MCP](https://www.anchorterminal.com/tools/lucid.md), 80/100 on security \u0026 auth, against 74 for the overall leader.\n- Transparency \u0026 trust: [Miro API + MCP](https://www.anchorterminal.com/tools/miro.md), 76/100 on transparency \u0026 trust, against 73 for the overall leader.\n- Self-hosting under an open licence: [Penpot API + MCP](https://www.anchorterminal.com/tools/penpot.md), self-hosted, MPL-2 licence.\n\n## How to choose\n\n- Read and write coverage: Check which objects the API can change as well as read, since an agent that can only read frames cannot apply the fixes it finds.\n- Auth scopes and access: Check that access scopes can be limited to single files, because a token that opens a whole team gives an agent more reach than the task needs.\n- Design-to-code and export formats: Check which export formats and design-to-code outputs are available, since an agent that turns a frame into code needs output it can parse without a manual step.\n- MCP tools and rate limits: List the MCP tools and their rate limits, because an agent that reads a canvas one frame at a time can hit a limit before the design is finished.\n\n## Each one in detail\n\n### 1. Figma API + MCP, B 66/100\n\nFigma's REST API and official MCP server connect applications and agents to its design platform.\n\n- Verdict: OpenAPI spec, TypeScript types and an llms.txt index for the REST API. View and Collab seats get 6 MCP calls a month on paid plans.\n- Choose it for: Design-to-code agents and teams already paying for Dev or Full seats.\n- Strength: OpenAPI spec, TypeScript types and an llms.txt index for the REST API\n- Strength: OAuth scopes per resource, plus plan access tokens with allowlists and expiry\n- Strength: MCP design context, screenshots and Code Connect for design-to-code work, with canvas writes on the remote server\n- Weakness: View and Collab seats get 6 MCP calls a month on paid plans\n- Weakness: MCP tools were unavailable for about 4 hours on 26 August 2026\n- Weakness: Only clients in Figma's MCP catalogue can connect\n- Price: $16 / seat-mo · Auth: OAuth or key · x402: no · Where: hosted\n- Full assessment: https://www.anchorterminal.com/tools/figma-mcp.md\n\n### 2. Miro API + MCP, B 65/100\n\nMiro's REST API v2 reads and writes boards and board items (sticky notes, shapes, connectors, frames, cards, text, images, documents), tags and members, so an agent can lay out diagrams as well as notes.\n\n- Verdict: REST creates shapes, connectors and frames, so flowcharts and architecture sketches can be drawn directly. Legacy MCP board tools were removed nine days after the deprecation notice.\n- Choose it for: Agents that draw diagrams, maps and planning boards people will keep editing.\n- Strength: REST creates shapes, connectors and frames, so flowcharts and architecture sketches can be drawn directly\n- Strength: Hosted MCP server with OAuth 2.1 on every plan including Free, and no delete tool in its 18\n- Strength: Published REST credit limits and MCP daily caps per plan\n- Weakness: Legacy MCP board tools were removed nine days after the deprecation notice\n- Weakness: No prompt-injection guidance for board content written by collaborators\n- Weakness: OAuth scopes are coarse (`boards:read`, `boards:write`)\n- Price: $8 / seat-mo · Auth: OAuth · x402: no · Where: hosted\n- Full assessment: https://www.anchorterminal.com/tools/miro.md\n- Against #1: https://www.anchorterminal.com/compare/figma-mcp-vs-miro.md\n\n### 3. Lucid API + MCP, C 60.6/100\n\nREST API and hosted MCP server for creating, reading and managing Lucidchart and Lucidspark diagrams.\n\n- Verdict: OAuth 2.0 scopes with `:readonly` variants, and audit log endpoints in the REST API. No public changelog for the API or the MCP server.\n- Choose it for: Organisations already on Lucid that want an agent to create or update diagrams inside governed workspaces, with read-only scopes and audit logs.\n- Strength: OAuth 2.0 scopes with `:readonly` variants, and audit log endpoints in the REST API\n- Strength: Mermaid in through REST, PlantUML sequence diagrams through MCP, both editable afterwards\n- Strength: Per-operation rate limits in each reference page's OpenAPI fragment, such as 60 a minute on Create Mermaid Diagram\n- Weakness: No public changelog for the API or the MCP server\n- Weakness: The status page doesn't monitor the API or the MCP server\n- Weakness: No single OpenAPI file and no official REST SDK\n- Price: $9 / seat-mo · Auth: OAuth or key · x402: no · Where: hosted\n- Full assessment: https://www.anchorterminal.com/tools/lucid.md\n\n### 4. Melius, C 54.1/100\n\nMelius is a hosted node-based canvas for generating images, video, audio and text with many third-party models. Outside agents read and write projects, canvases, nodes, edges, runs and comments through a REST API, an MCP server and the mel CLI.\n\n- Verdict: 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 shows no incidents since July 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.\n- Choose it 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.\n- Strength: Public OpenAPI 3.0.2 spec with 59 operations, plus llms.txt, llms-full.txt and a Markdown copy of every docs page\n- Strength: Hosted MCP server with OAuth sign-in (PKCE, dynamic client registration) or a bearer API key, tied to one team chosen at authorisation\n- Strength: 429 responses carry `Retry-After` and `retryAfterSeconds`, and the docs give a bounded retry policy\n- Weakness: API keys have no scopes. A key works with its creator's role in every team the creator belongs to\n- Weakness: No rate-limit numbers, SLA, public changelog or API deprecation policy found in the reviewed documentation\n- Weakness: The MCP reference lists 75 tools, and the setup guide tells users to select Always Allow for all of them\n- Price: $20 / mo · Auth: OAuth or key · x402: no · Where: hosted\n- Full assessment: https://www.anchorterminal.com/tools/melius.md\n- Against #1: https://www.anchorterminal.com/compare/figma-mcp-vs-melius.md\n\n### 5. Sketch, D 53.5/100\n\nMac design application from Sketch B.V. with a built-in local MCP server. Connected AI clients read open documents, layers, symbols and libraries, take screenshots, and run scripts against the Sketch JavaScript API to edit designs.\n\n- Verdict: 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.\n- Choose it 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.\n- Strength: Eight tools, seven marked read-only and `run_code` marked destructive in the connector source\n- Strength: `run_code` runs scripts against the documented Sketch JavaScript API, so an agent can create, edit and export layers\n- Strength: The server is off by default and listens on localhost only, per the docs\n- Weakness: No credential or token is documented for the local server at port 31126\n- Weakness: No read-only mode. `run_code` is always listed, and approval depends on the connected client\n- Weakness: Needs the Mac app running with a document open. No hosted or headless route was found\n- Price: $12 / seat-mo · Auth: None · x402: no · Where: local\n- Full assessment: https://www.anchorterminal.com/tools/sketch.md\n- Against #1: https://www.anchorterminal.com/compare/figma-mcp-vs-sketch.md\n\n### 6. Framer Server API, D 52.6/100\n\nFramer is a website builder with a design canvas.\n\n- Verdict: Same surface as the Plugin API, so canvas nodes, components, code files and CMS are writable. No REST endpoints and no official MCP server. You need Node 22 and the `framer-api` package.\n- Choose it for: Coding agents that build or update Framer sites, CMS content and code components and can run Node.\n- Strength: Same surface as the Plugin API, so canvas nodes, components, code files and CMS are writable\n- Strength: `@framer/agent` puts every agent change on a branch and limits it to the projects you connect\n- Strength: Publish makes a preview deployment that a separate `deploy` promotes\n- Weakness: No REST endpoints and no official MCP server. You need Node 22 and the `framer-api` package\n- Weakness: Open beta with no published rate limits, price or SLA\n- Weakness: Not transactional, so failures can leave partial edits\n- Price: $10 / mo · Auth: API key · x402: no · Where: local\n- Full assessment: https://www.anchorterminal.com/tools/framer.md\n- Against #1: https://www.anchorterminal.com/compare/figma-mcp-vs-framer.md\n\n### 7. pen.dev, D 47.6/100\n\nDesign canvas from High Agency, Inc. that stores designs as JSON `.pen` files. Agents edit them through a local MCP server in the desktop app or IDE extension, or through a headless CLI. It was called Pencil until 2026.\n\n- Verdict: An agent can create, edit and export `.pen` designs without a GUI through the `pen` CLI, with four compact MCP tools that carry annotations and a documented JSON format. The software is closed and needs a pen.dev account. No changelog, status page or security contact was found, and 14 public issue reports had no reply on 8 October 2026.\n- Choose it for: A coding agent that designs screens beside the code and keeps them in Git, including in CI.\n- Strength: Headless CLI (`@pen.dev/cli`) runs the same editor engine as the desktop app and exports PNG, JPEG, WEBP, PDF and HTML\n- Strength: Four standard MCP tools with typed inputs and readOnlyHint and destructiveHint annotations, plus two conditional tools\n- Strength: The `.pen` format is JSON with a published TypeScript schema, so designs sit in Git beside code\n- Weakness: No changelog. The three desktop releases on GitHub have empty notes, and the format docs reserve the right to make breaking changes\n- Weakness: 14 issues opened between 28 July and 6 October 2026 in highagency/pen-desktop-releases had no comment or closure on 8 October\n- Weakness: No status page, security.txt, disclosure policy, bug bounty or certification was found\n- Price: $16 / seat-mo · Auth: OAuth or key · x402: no · Where: local\n- Full assessment: https://www.anchorterminal.com/tools/pen-dev.md\n- Against #1: https://www.anchorterminal.com/compare/figma-mcp-vs-pen-dev.md\n\n### 8. Zeplin, D 47.5/100\n\nDesign handoff platform from Zeplin, Inc. where teams publish finished screens, components and design tokens. Its REST API and webhooks read and partly edit that data, and an official local MCP server gives coding agents screen and component specifications.\n\n- Verdict: The API documents 123 operations with typed parameters, a 200-requests-a-minute limit and OAuth with PKCE, and every plan includes it. Tokens carry no scopes, no status page was found on the pages read, and the API changelog's last entry is dated 11 May 2021.\n- Choose it for: Teams that already publish designs to Zeplin and want an agent to read screens, components, tokens and notes, or turn a screen into code through the MCP server.\n- Strength: 123 documented operations, each with an OpenAPI 3.0.2 definition in a Markdown twin, indexed by `llms.txt`\n- Strength: Rate limit stated as 200 requests a minute per user, with `Zeplin-RateLimit-Limit`, `-Remaining` and `-Reset` response headers\n- Strength: OAuth 2.0 authorisation code grant with PKCE, one-hour access tokens and single-use refresh tokens\n- Weakness: OAuth tokens and personal access tokens carry no scopes. The OpenAPI security scheme lists none\n- Weakness: No status page is linked from the site, docs or help centre pages read\n- Weakness: The API changelog's last entry is 11 May 2021, though the reference has since gained variables, flow boards and annotations\n- Price: $13.75 / mo · Auth: OAuth or key · x402: no · Where: local\n- Full assessment: https://www.anchorterminal.com/tools/zeplin.md\n- Against #1: https://www.anchorterminal.com/compare/figma-mcp-vs-zeplin.md\n\n### 9. Penpot API + MCP, E 43.5/100\n\nOpen-source design and prototyping tool, used as SaaS at design.penpot.app or self-hosted.\n\n- Verdict: MPL-2.0 and self-hostable, with API, webhooks and MCP on the free cloud plan. Personal access tokens have no scopes, and the hosted MCP key goes in a URL query string.\n- Choose it for: Teams that want design files on their own servers and an agent working alongside a person in the editor.\n- Strength: MPL-2.0 and self-hostable, with API, webhooks and MCP on the free cloud plan\n- Strength: MCP `execute_code` reaches the whole plugin API, so an agent can create, move, restyle and delete shapes\n- Strength: OpenAPI description served by every instance\n- Weakness: Personal access tokens have no scopes, and the hosted MCP key goes in a URL query string\n- Weakness: No annotations on MCP tools and no read-only mode\n- Weakness: Four advisories in 2026, including MCP REPL remote code execution\n- Price: $7 / seat-mo · Auth: Token · x402: no · Where: hosted\n- Full assessment: https://www.anchorterminal.com/tools/penpot.md\n- Against #1: https://www.anchorterminal.com/compare/figma-mcp-vs-penpot.md\n\n### 10. Subframe, E 39.7/100\n\nDesign tool from Atomic Design Inc for React and Tailwind interfaces, with a cloud canvas and a macOS app. Agents read and edit pages, components and themes through a hosted MCP server, and a CLI syncs components into a codebase.\n\n- Verdict: An agent can read and change pages, components, snippets and themes in a Subframe project through a hosted MCP server with OAuth, and Viewer accounts get a read-only server. The server lists 46 tools, and no status page, rate limits, changelog or security contact were found. Three tools were renamed in September 2026 with no notice found.\n- Choose it for: A coding agent working beside a team that designs React and Tailwind interfaces in Subframe and wants the design as code, with a read-only route for review.\n- Strength: Hosted MCP server at `https://mcp.subframe.com/mcp` with OAuth, dynamic client registration and PKCE, so no key is pasted into a config file\n- Strength: Viewer accounts get a read-only MCP server and read-only CLI access, and Viewer seats are free on every plan\n- Strength: Write tools cover pages, components, snippets, design documents, themes, icons and fonts, and page reads return generated React and Tailwind code\n- Weakness: 46 tools are documented with no toolsets, and the vendor's `design` skill that explains them is about 55 KB of text\n- Weakness: No status page, published rate limit, SLA or changelog was found, and the terms disclaim uninterrupted service\n- Weakness: `list_flows`, `get_flow_info` and `delete_flow` became `list_canvases`, `get_canvas_info` and `delete_canvas` in September 2026 with no notice found\n- Price: $20 / seat-mo · Auth: OAuth or key · x402: no · Where: hosted\n- Full assessment: https://www.anchorterminal.com/tools/subframe.md\n- Against #1: https://www.anchorterminal.com/compare/figma-mcp-vs-subframe.md\n\n## Head to head\n\n- [Figma API + MCP vs Miro API + MCP](https://www.anchorterminal.com/compare/figma-mcp-vs-miro.md)\n- [Figma API + MCP vs Melius](https://www.anchorterminal.com/compare/figma-mcp-vs-melius.md)\n- [Figma API + MCP vs Sketch](https://www.anchorterminal.com/compare/figma-mcp-vs-sketch.md)\n- [Melius vs Miro API + MCP](https://www.anchorterminal.com/compare/melius-vs-miro.md)\n- [Miro API + MCP vs Sketch](https://www.anchorterminal.com/compare/miro-vs-sketch.md)\n- [Melius vs Sketch](https://www.anchorterminal.com/compare/melius-vs-sketch.md)\n\n## Questions\n\n### What are the highest-rated design workspace and canvas APIs for AI agents?\n\nFigma API + MCP has the highest benchmark score of the 10 ranked design workspace and canvas APIs, 66 (B). Miro API + MCP is second with 65 (B).\n\n### How many design workspace and canvas APIs are agent-ready?\n\n0 of the 10 ranked here grade BB or better, the bar for agent-ready on the Anchor benchmark.\n\n### Which design workspace and canvas APIs accept x402 payments?\n\nNone of the ranked listings here accepts x402 for its main call yet.\n\n### How is this list ranked?\n\nBy the Anchor benchmark score out of 100, a weighted mean of the scored categories minus deductions for negative events, from public evidence re-checked as vendors change. Listings cannot pay for a place. The latest assessment behind this page is from 9 October 2026.\n\n## How this list is made\n\nThe order is the Anchor benchmark score, the same number as on each listing. Each listing is graded from public evidence against the benchmark checklist, and the picks are worked out from those grades, prices and facts. No listing pays for its place, and paid audits or listing help never change a score.\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-10", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Best of", "url": "https://www.anchorterminal.com/best/" }, { "name": "Design workspaces \u0026 canvases", "url": "" } ], "description": "Figma API + MCP (B), Miro API + MCP (B) and Lucid API + MCP (C) lead the 10 ranked design workspace and canvas APIs. Picks by need, strengths, weaknesses and prices from the Anchor benchmark.", "facts": [ "Figma API + MCP B", "Miro API + MCP B", "Lucid API + MCP C" ], "h1": "Best design workspace and canvas APIs for AI agents", "image": "https://www.anchorterminal.com/assets/og/best-design.png", "path": "/best/design/", "published": "", "section": "tools", "title": "Best design workspace and canvas APIs for AI agents in 2026, ranked", "toc": null, "updated": "2026-10-09", "url": "https://www.anchorterminal.com/best/design/" }, "tokens": { "markdown": 5250, "slim": 1280 }, "version": 1 }