Guide

Design MCP Servers Compared (2026): Figma, Canva, Webflow, Wix, Miro, Cloudinary

Which design MCP server should my AI agent use (Figma, Canva, Webflow, Wix, Miro or Cloudinary), and what plan does each need?

For design to code, use Figma's remote MCP server: it reads design context, variables and screenshots from a Figma file, and real use needs a Dev or Full seat on a paid plan (Starter gets 20 tool calls a month). To build or edit a website, use Webflow's server for visual and CMS edits, or the Wix MCP to create, publish and manage Wix sites; both connect with OAuth to a hosted URL. Use Canva for marketing designs (most tools work on the free plan), Miro for whiteboards (free plan, 100 calls a day), and Cloudinary for uploading, searching and transforming images and video (free plan, 25 credits a month).

Compare: the best MCP servers for scraping, search, browsers, databases, hosting, monitoring, payments, auth and design →

Coding agent settings change often

Get one email a week when a setting, flag or permission rule changes, checked against the vendor docs.

Quick comparison

  • Figma: hosted at https://mcp.figma.com/mcp, or a desktop server at http://127.0.0.1:3845/mcp. Reads design context, variables, screenshots and Code Connect maps; use_figma and other write tools edit files. Sign in with your Figma account. Starter (free): 20 tool calls a month. Professional Full or Dev seat: 200 calls a day.
  • Canva: hosted, OAuth per user, added in Claude from the connectors list. Generate, edit, search, comment on and export designs. Most tools work on all plans, including Free. Resize, autofill, brand kits and brand templates need Pro or above (Pro is US$144 a year).
  • Webflow: hosted at https://mcp.webflow.com/mcp with OAuth, or local npx webflow-mcp-server@latest with WEBFLOW_TOKEN. Edits pages, elements, styles, components and the CMS. A few tools need the Designer open with the MCP Bridge App. Webflow's pricing page lists the MCP server on the free Starter site plan.
  • Wix: hosted at https://mcp.wix.com/mcp; signs in through your Wix account, or an API key plus account ID. Creates, updates and publishes sites, and calls site APIs such as Stores, Bookings and CMS. The MCP docs list no plan requirement.
  • Miro: hosted at https://mcp.miro.com with OAuth 2.1. Reads boards as SVG, creates and updates board items, diagrams, prototypes and comments. All plans: Free 100 calls a day, Starter 500, Business 2,000, Enterprise 10,000.
  • Cloudinary: several hosted servers (Asset Management, Environment Config, Structured Metadata, Analysis, MediaFlows) with OAuth or API keys, plus local npx packages. Upload, search, manage and transform media. Free plan: 25 monthly credits, no card. Plus: $99 a month billed monthly.
  • Prices, limits and tool lists were checked on each vendor's docs and pricing pages on 2026-10-23 and change often.

Figma MCP (design to code)

Figma's MCP server gives the agent design context from a Figma file so it can write code that matches. Figma recommends the remote server, which connects to Figma's hosted endpoint and does not need the desktop app. The desktop server runs locally through the Figma desktop app and needs a Dev or Full seat on a paid plan. You sign in with your Figma account the first time you connect. Figma's docs say only clients in its MCP catalog can connect.

Claude Code, remote server (recommended plugin)

claude plugin install figma@claude-plugins-official

Claude Code, remote server without the plugin

claude mcp add --scope user --transport http figma https://mcp.figma.com/mcp

Any agent, remote (mcpServers JSON)

{
  "mcpServers": {
    "figma": {
      "url": "https://mcp.figma.com/mcp"
    }
  }
}

Claude Code, desktop server

claude mcp add --transport http figma-desktop http://127.0.0.1:3845/mcp
  • Read tools: get_design_context, get_variable_defs, get_screenshot, get_metadata, get_code_connect_map, search_design_system (remote only), download_assets (remote only), get_figjam.
  • Write tools (remote only unless noted): use_figma creates, edits and inspects content in Figma files; also create_new_file, generate_diagram, generate_figma_design, html_to_figma, upload_assets, and add_code_connect_map (both servers).
  • Writing to the canvas needs the remote server and a Full seat to write outside your drafts. Figma says it is free during the beta and will become a usage-based paid feature.
  • Limits: Starter, and View or Collab seats on any plan, get 20 tool calls a month. Professional Full or Dev seats get 200 a day and 10 a minute; Organization 200 a day and 15 a minute; Enterprise 600 a day and 20 a minute.
  • Price: Professional lists a Dev seat at $12/mo and a Full seat at $16/mo.
  • Desktop server: open a Design file, switch to Dev Mode with nothing selected, and click Enable desktop MCP server in the right sidebar.

Canva MCP (marketing designs)

Canva's MCP server is hosted by Canva and lets the agent create, edit, search and export designs in your Canva account. Each user signs in with OAuth; Canva does not support one shared login for a whole organization. In Claude, add Canva from Settings, Connectors. Canva's docs we checked do not publish a server URL for manual setup.

  • Main tools: generate-design, create-design, search-designs, get-design-content, start-editing-transaction, perform-editing-operations, commit-editing-transaction, export-design, upload-asset-from-url, comment-on-design, resize-design, autofill-design.
  • Plans: most tools are on all plans, including Free. resize-design, autofill-design, brand kits and brand templates are Pro and above. Free users get a limited trial of resize-design.
  • Export works on all plans, but the plan affects output quality, and designs with premium elements can fail with license_required.
  • Rate limit: 300 requests a minute per user across all MCP clients, with lower limits on some tools (for example generate-design at 20 a minute).
  • Gotcha: Canva's Help Center pages give different plan rules for autofill than the developer tools table (Pro and above). Check your plan if autofill fails.
  • Separate product: the Canva Dev MCP server (claude mcp add canva-dev -- npx -y @canva/cli@latest mcp) helps you build Canva apps. It is not for editing your designs.

Webflow MCP (build and edit sites)

Webflow's MCP server can change a site's design (layouts, elements, styles, components, interactions), work with the CMS, create pages and read analytics. You connect with OAuth and pick which sites it can reach. Agents can do only what your Webflow role allows. Most tools work without the Designer open; snapshots, image uploads and reading or changing the current selection, page or breakpoint need the Designer open with the MCP Bridge App running.

Claude Code, hosted endpoint with OAuth

claude mcp add --transport http webflow https://mcp.webflow.com/mcp

Any agent, local (mcpServers JSON)

{
  "mcpServers": {
    "webflow": {
      "command": "npx",
      "args": ["-y", "webflow-mcp-server@latest"],
      "env": { "WEBFLOW_TOKEN": "YOUR_WEBFLOW_TOKEN" }
    }
  }
}
  • Main tools: data_sites_tool, data_pages_tool, data_cms_tool, data_element_builder, data_element_tool, data_style_tool, data_component_tool, data_assets_tool, data_localization_tool, data_scripts_tool.
  • Limits: each authorization covers one workspace. The agent cannot create new site projects; make the site in the dashboard first. Page branches need an Enterprise plan.
  • Free tier: Webflow's pricing page lists the MCP server on the free Starter site plan (webflow.io domain, 2 static pages, limited CMS).
  • Gotcha: the GitHub README lists the remote URL as https://mcp.webflow.com/sse; the developer docs use https://mcp.webflow.com/mcp, which we follow.

Wix MCP (build and manage sites)

The Wix MCP lets the agent search Wix docs, write code for Wix, call APIs on your sites, and create and publish sites. It is a built-in connector in Claude. By default it signs in through your Wix account; for tools with no interactive login, use an API key and your Wix account ID. Wix lists Node.js 19.9.0 or higher as a prerequisite.

Claude Code, hosted endpoint

claude mcp add --transport http wix-mcp-remote https://mcp.wix.com/mcp

Agents without remote MCP (mcpServers JSON)

{
  "mcpServers": {
    "wix-mcp-remote": {
      "command": "npx",
      "args": ["-y", "@wix/mcp-remote@latest", "https://mcp.wix.com/mcp"]
    }
  }
}
  • Main tools: WixREADME, ListWixSites, GetSiteContext, ManageWixSite (create, update or publish a site), CallWixSiteAPI, ExecuteWixAPI (Bookings, Stores, CMS), UploadImageToWixSite, plus documentation search tools.
  • API key setup: send Authorization and wix-account-id headers; the local proxy reads WIX_API_KEY.
  • Gotcha: if the connection drops after a long idle period or after switching Wix accounts, delete ~/.mcp-auth and reconnect.
  • Do not confuse it with the Wix Site MCP at <your-site>/_api/mcp. That one lets visitors' agents use a live site as an anonymous visitor and cannot edit it.

Miro MCP (whiteboards)

Miro's MCP server is hosted by Miro, and clients must support remote connections. It reads board content and creates or updates boards, diagrams, prototypes and comments. You sign in with OAuth 2.1 and pick one Miro team; the agent sees only boards in that team. On Enterprise, an admin must enable MCP first.

Claude Code, hosted endpoint with OAuth

claude mcp add --transport http miro https://mcp.miro.com
  • Main tools: board_search_boards, board_create, canvas_search, canvas_read_as_svg, canvas_create_from_svg, canvas_update_from_svg, prototype_read, prototype_create, comment_list_comments, comment_reply, image_create.
  • Daily tool-call limits reset at 00:00 UTC: Free 100, Starter 500, Business 2,000, Enterprise 10,000.
  • Price: Starter $8 and Business $20 per member a month, billed yearly.
  • Gotcha: older board_list_items, context_*, layout_*, diagram_* and doc_* tools were removed, so old prompts that name them will fail. The table_* tools are marked as deprecating soon.

Cloudinary MCP (images and video)

Cloudinary runs several MCP servers. Asset Management uploads and manages images, videos and raw files with search and filtering. Environment Config manages upload presets and named transformations. Structured Metadata manages metadata fields. Analysis does AI tagging and needs OAuth. MediaFlows builds media automations. Remote servers use OAuth by default, or API credentials in headers; MediaFlows does not use OAuth and takes credentials in headers only.

Any agent, remote with OAuth (JSON)

{
  "mcpServers": {
    "cloudinary-asset-mgmt": {
      "url": "https://asset-management.mcp.cloudinary.com/mcp"
    }
  }
}

Remote with API key (header)

{
  "mcpServers": {
    "cloudinary-asset-mgmt": {
      "url": "https://asset-management.mcp.cloudinary.com/mcp",
      "headers": {
        "cloudinary-url": "cloudinary://api_key:api_secret@cloud_name"
      }
    }
  }
}
  • Other remote URLs: https://environment-config.mcp.cloudinary.com/mcp, https://structured-metadata.mcp.cloudinary.com/mcp, https://analysis.mcp.cloudinary.com/sse, https://mediaflows.mcp.cloudinary.com/v2/mcp.
  • Local: the npx packages read CLOUDINARY_CLOUD_NAME, CLOUDINARY_API_KEY and CLOUDINARY_API_SECRET (the Asset Management README also accepts CLOUDINARY_URL). Find credentials on the API Keys page in Console Settings. Package names differ between the docs (@cloudinary/asset-management) and the GitHub README (@cloudinary/asset-management-mcp); use the docs name.
  • Asset Management custom tools: transform-asset and get-tx-reference. Run with --mode dynamic to load tools on demand.
  • Free plan: 25 monthly credits, 3 users, no credit card. Plus: $99 a month billed monthly, or $89 a month billed yearly.
  • Gotcha: Cloudinary's docs give Claude Code commands with --transport sse, which we follow; its GitHub README says the /mcp endpoints are Streamable HTTP and /sse is deprecated. MediaFlows uses different header names (cld-cloud-name, cld-api-key, cld-secret).

Which one to pick

  • Design to code: Figma remote server. Budget for a Professional Dev or Full seat; the free Starter plan's 20 calls a month is only enough to try it.
  • Build a website: Webflow if you want precise control of layout, styles and the CMS. Wix if you want the agent to create and publish a site and manage store, bookings or CMS data.
  • Edit marketing designs: Canva. Free covers generating, editing and exporting; brand templates and resizing need Pro.
  • Whiteboards: Miro. The free plan's 100 calls a day is enough for reading boards and drafting diagrams.
  • Image and video assets: Cloudinary Asset Management, with Environment Config if the agent should manage upload presets.
  • Prefer the OAuth endpoints, so no API keys end up in committed config files.
  • All details on this page were checked against vendor docs and pricing pages on 2026-10-23.

Get coding agent settings changes by email

When a setting, flag or permission rule in this guide changes, it goes in the weekly AgentAtlas update, checked against the vendor docs. One email a week.

Sources

More guides

Other guides

How to allow Cursor to run all commands: Run Everything, allowlist and sandboxHow to allow Claude Code to run all commands: permission modes, allow rules and skip permissionsClaude Code permissions: allow, ask and deny rules, rule syntax and allowed toolsCodex CLI: approval and sandbox modesGemini CLI: YOLO mode, auto_edit and allowing specific shell commandsCursor Privacy Mode: telemetry, training and data retentionClaude Code telemetry and data retention: what is sent and how to turn it offGemini CLI: turn off usage statistics and telemetryCLAUDE.md: where it goes, how it loads, and how it works with AGENTS.mdClaude Code hooks: all events, exit codes, PreToolUse and PermissionRequest JSON, examplesClaude Code subagents: create one, limit its tools, and call itAdd MCP servers to Cursor with mcp.json: Keep files out of Cursor with .cursorignore: Configure Codex with config.toml: Configure Gemini CLI with settings.json: Add MCP servers to Claude Code (claude mcp add, .mcp.json, scopes): Claude Code custom slash commands and skills (SKILL.md): GitHub Copilot custom instructions: Adding MCP servers to GitHub Copilot: Claude Code settings.json: file locations, precedence, and key settingsClaude Code plugins and marketplaces: install, create, and shareGemini CLI extensions and custom commands: Configuring OpenCode with opencode.json: Cline Rules: workspace, global, and conditional rulesKiro steering files: .kiro/steering, inclusion modes, and AGENTS.mdZed agent: instruction files, MCP servers, tool permissions, and ACP agentsCursor CLI: install, headless mode, permissions and CIAider: CONVENTIONS.md, .aider.conf.yml and API keysJunie guidelines, MCP and the Action Allowlist: Amp AGENTS.md, settings.json and MCP: Configure Goose extensions, hints, recipes and permissions: Customize OpenHands with skills, AGENTS.md, setup.sh and MCP: Configure Factory Droid CLI: AGENTS.md, settings.json, autonomy, custom droids and MCPConfigure Qwen Code: settings.json, providers, QWEN.md, MCP and approval modesCursor hooks: hooks.json, beforeShellExecution, afterFileEdit and exit codesCursor sandbox: sandbox.json, network allowlist and run modesCursor settings: settings.json, Cursor Settings and the ~/.cursor config filesCursor browser agent: @browser, browser automation and approval modesCursor subagents: .cursor/agents, frontmatter, built-in Explore and BrowserCursor telemetry and OpenTelemetry export (Privacy Mode, OTLP, Analytics API): Cursor rules setup: project, user and Team Rules, .mdc frontmatter, globs and AGENTS.mdClaude Code headless mode: claude -p, --output-format json, --bare and CI flagsClaude Code statusline: custom status bar in settings.json with context %, cost and git branchClaude Code /model: switch models, aliasesClaude Code /cost and /usage: check token spend, usage limits and reduce costsClaude Code VS Code extension: install, shortcuts, settings and /ideCodex AGENTS.md: global, project and override instruction files explainedCodex MCP servers: codex mcp add and [mcp_servers] in config.tomlCodex sandbox modes: read-only, workspace-write, danger-full-access and network accesscodex exec: run Codex non-interactively in scripts and CI with JSON outputCodex skills: create SKILL.md, skill folder locations and $skill invocationGEMINI.md in Gemini CLI: context file locations, imports and /memoryGemini CLI MCP servers: gemini mcp add and mcpServers in settings.jsonGemini CLI custom slash commands: TOML files, {{args}}, !{shell} and @{file}Gemini CLI headless mode: gemini -p, JSON output and exit codes for scripts and CIGemini CLI sandbox: enable Docker, Podman, macOS Seatbelt or gVisorcopilot-setup-steps.yml: set up the GitHub Copilot cloudGitHub Copilot CLI permissions: --allow-tool, --deny-tool, --allow-all-tools and trusted directoriesGitHub Copilot custom agents: .github/agents/*.agent.md profiles, tools and frontmatterGitHub Copilot code review settings: automatic PR reviews, rulesets, effort level and approvalsOpenCode MCP Server Setup: Local and Remote Servers in opencode.jsonOpenCode Permissions: Allow, Ask or Deny Bash, Edit and WebfetchOpenCode Custom Agents and Subagents: Markdown Files, Modes and @ MentionsCline MCP Setup: cline_mcp_settings.json for Local and Remote ServersCline Auto Approve and YOLO Mode: Run Commands and Edits Without PromptsCline Skills: SKILL.md Location, Format and Slash Command UseAmp MCP Setup: amp mcp add, amp.mcpServers and Workspace ApprovalAmp AGENTS.md: File Locations, @ Mentions and Glob-Scoped GuidanceAmp Skills: SKILL.md Folders, amp skill add and Search OrderKiro MCP Setup: .kiro/settings/mcp.json, autoApprove and OAuthKiro Hooks: .kiro/hooks JSON, PreToolUse, PostFileSave and StopKiro Permissions: permissions.yaml Allow, Ask and Deny RulesFactory Droid MCP Setup: droid mcp add, mcp.json Locations and /mcpFactory Droid Hooks: hooks.json, PreToolUse Matchers and Exit CodesFactory Droid Custom Droids (Subagents): .factory/droids Markdown FilesJunie MCP Setup: .junie/mcp/mcp.json for CLI and /mcp CommandJunie Brave Mode and Action Allowlist: Auto-Approve Commands in Junie CLIJunie Custom Slash Commands: .junie/commands Markdown Files and Argumentsgoose .goosehints and AGENTS.md: Global and Project Instructionsgoose Permission Modes: GOOSE_MODE auto, approve, smart_approve and chatgoose Recipes: recipe.yaml Format, Parameters and goose run --recipeZed Agent Tool Permissions: Auto-Approve Terminal Commands with tool_permissionsUse Claude, Codex and Gemini CLI in Zed: External Agents and agent_serversZed with Ollama, LM Studio and llama.cpp: Local Model Setup and Context LengthMCP 2026-07-28 Migration Guide: Stateless Protocol, No Sessions, server/discover, MRTR, and SDK v2 UpgradeSubagents and Custom Agents Compared: Claude Code vs Codex vs Cursor vs Gemini CLI vs GitHub CopilotAllow all commands in any AI coding agent: Cursor, Claude Code, Codex, Gemini CLI, Copilot CLI and 7 moreSettings file locations for every AI coding agent: Claude Code, Cursor, Codex, Gemini CLI, OpenCode, Qwen Code, Amp and Factory DroidRules and instruction files in every AI coding agent: .cursor/rules, CLAUDE.md, AGENTS.md, GEMINI.md, Copilot instructions and moreGemini CLI hooks: settings.json, BeforeTool, AfterTool, exit codes and /hooksGitHub Copilot hooks: .github/hooks/*.json for Copilot CLI and the cloud agentHooks in every AI coding agent: Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Kiro and Factory DroidAgent Skills (SKILL.md) in every AI coding agent: Claude Code, Codex, Cline, Amp and OpenHandsHow to deploy a remote MCP server (Streamable HTTP): Cloudflare Workers, Vercel, Railway and moreHeadless mode in every AI coding agent: claude -p, codex exec, gemini -p, Cursor agent -p and copilot -p for scripts and CIClaude Code sandbox: /sandbox, sandbox.enabled, allowedDomains, excludedCommands and strict modeSandbox modes in every AI coding agent: Claude Code, Cursor, Codex and Gemini CLI comparedCustom slash commands in every AI coding agent: file locations, arguments and examplesMigrate from Gemini CLI to Antigravity CLI (2026): Config, MCP, Skills, FlagsRun GitHub Copilot CLI with copilot -p in scripts and CI (2026): Agent Loops 2026: Ralph Loop, /loop, /goal and Headless Loops for AI Coding AgentsCursor skills and custom slash commands: .cursor/skills SKILL.md, .cursor/commands and /migrate-to-skillsCodex hooks: hooks.json, PreToolUse allow/deny, exit code 2 and config.toml [hooks]GitHub Copilot prompt files in VS Code: .github/prompts/*.prompt.md slash commandsOpenCode custom commands: .opencode/commands, $ARGUMENTS, shell output and subtasksQwen Code custom commands: .qwen/commands Markdown files, {{args}}, !{shell} and @{file}

Reviewed Oct 23, 2026. Settings change often; the linked vendor docs are the source of truth.