Skip to main content
Glama
590,899 tools. Updated 2026-09-20 08:37

"Blackmagic Design" matching MCP tools:

  • Get the Designesy Design Review framework — an 8-dimension rubric (Purpose, Clarity, Context, Inclusion, System coherence, Durability, Delight, Responsibility) plus the agent prompt, output format, and verification checklist for a qualitative design critique. Use this when you want a structured rubric to critique a design holistically, rather than a numeric compliance score. When NOT to use: for a deterministic numeric score, use designesy_score; this tool gives you a rubric, not a number. Read-only — returns the rubric + prompt. The calling agent performs the actual critique (this tool does not evaluate the design for you). Returns JSON: { rubric, dimensions[8], agent_prompt, output_format, verification_checklist }. Pass artifact/purpose/context/rules to get a pre-filled critique prompt; omit all four to get the blank framework.
    ConnectorNo auth
  • Diff two design systems from live URLs — the only URL-scoped design-token diff engine. Fetches both URLs in parallel, extracts their :root custom properties, and produces a structured diff across 8 dimensions: tokens added (in A not B), removed (in B not A), renamed (heuristic Levenshtein ≤ 2), value-changed (same name, different value), scale-stop-changed (spacing/radius/color scale steps), contrast-drift-per-pair (WCAG contrast ratio change for shared color tokens), structure-delta (token count + category distribution), and score-delta (runs /score on both URLs and diffs). Use this to answer "what actually changed between two design systems" or "how does our design system differ from a reference". When NOT to use: for single-site drift detection, use designesy_drift_score; for continuous monitoring, use designesy_monitor_score. Executable — fetches both URLs, extracts CSS + tokens, computes diff. No browser needed. Returns JSON: { ok, urlA, urlB, score (0-100, diff completeness), grade, pass, warn, fail, total, tokensA, tokensB, added[], removed[], renamed[], valueChanged[], scaleDiff, structureDelta, contrastDrift[], scoreDelta, checks[] }. Results cached ~24h per URL pair.
    ConnectorNo auth
  • Get the text content of a doc, presentation, whiteboard, social media post, and other designs in Canva (except sheets, as it does not return data in sheets). Use this when you only need to read text content without making changes. IMPORTANT: If the user wants to edit, update, change, translate, or fix content, use `start-editing-transaction` instead as it shows content AND enables editing. You must provide the design ID, which you can find with the `search-designs` tool. You may also pass a full Canva design share URL directly (do not pre-extract just the ID) — any collaboration token embedded in the URL is needed to access a design shared via link and will be parsed and forwarded automatically. Do not use web search to get the content of a design as the content is not accessible to the public. Example URL: https://www.canva.com/design/{design_id}.
    ConnectorOAuth
  • LEGACY-ONLY — DO NOT CALL WHEN create-design IS AVAILABLE. If create-design is in the tool list, you MUST NOT call this tool. Call create-design instead. All instructions below apply only when create-design is absent from the tool list. A failed create-design call does not make it unavailable. Generate professionally designed content in Canva including visual designs (posters, social media posts, presentations, flyers) and text-based documents (memos, articles, newsletters, proposals, reports, business plans, requirements documents). Each extra slide adds significant latency (e.g. 15 slides can take 3x longer than 5). Keep to 1-5 slides unless the user explicitly requests more. Use this tool when the user asks you to write, create, generate, or draft ANY document or visual design. Examples: - "Write a memo..." → use this tool to create a Canva Doc - "Generate a business proposal..." → use this tool to create a Canva Doc - "Draft a product overview..." → use this tool to create a Canva Doc DO NOT use this tool for fixed-format visual designs when prepare-design-generation is available. Do NOT use this tool when the user just wants advice, explanations, or information. DO NOT use this tool when the user's message contains a URL and their intent is to create a design FROM that URL — use import-design-from-url instead. Use the 'query' parameter to tell AI what you want to create. The tool doesn't have context of previous requests. ALWAYS include details from previous queries for each iteration. The tool provides best results with detailed context. ALWAYS look up the chat history and provide as much context as possible in the 'query' parameter. Ask for more details when the tool returns this error message 'Common queries will not be generated'. The generated designs are design candidates for users to select from. Ask for a preferred design and use 'create-design-from-candidate' tool to add the design to users' account. The IDs in the URLs are not design IDs. Do not use them to get design or design content. When using the 'asset_ids' parameter, assets are inserted in the order provided. For small designs with few image slots, only supply the images the user wants. For multi-page designs like presentations, supply images in the order of the slides. The tool will return a list of generated design candidates, including a candidate ID, preview thumbnail and url. Before editing, exporting, or resizing a generated design, follow these steps: 1. call 'create-design-from-candidate' tool with 'job_id' and 'candidate_id' of the selected design 2. call other tools with 'design_id' in the response For presentations, target 1-5 slides by default (length: "short"). Format the query string with these sections in order (use the headers exactly): 1. **Presentation Brief** Include: * **Title** (working title for the deck) * **Topic / Scope** (1–2 lines; include definitions if terms are uncommon) * **Key Messages** (3–5 crisp takeaways) * **Constraints & Assumptions** (timebox, brand, data limits, languages, etc.) * **Style Guide** (tone, color palette, typography hints, imagery style) 2. **Narrative Arc** A one-paragraph outline of the story flow (e.g., Hook → Problem → Insight → Solution → Proof → Plan → CTA). Keep transitions explicit. 3. **Slide Plan** Provide numbered slides with **EXACT titles** and detailed content. For each slide, include all of the following subsections in this order (use the labels exactly): * **Slide {N} — "{Exact Title}"** * **Goal:** one sentence describing the purpose of the slide. * **Bullets (3–6):** short, parallel phrasing; facts, examples, or specifics (avoid vague verbs). * **Visuals:** explicit recommendation (e.g., "Clustered bar chart of X by Y (2022–2025)", "Swimlane diagram", "2×2 matrix", "Full-bleed photo of <subject>"). * **Data/Inputs:** concrete values, sources, or placeholders to be filled (if unknown, propose realistic ranges or example figures). * **Speaker Notes (2–4 sentences):** narrative details, definitions, and transitions. * **Asset Hint (optional):** reference to an asset by descriptive name or index if assets exist (e.g., "Use Asset #3: 'logo_dark.svg' as corner mark"). * **Transition:** one sentence that logically leads into the next slide. > Ensure the Slide Plan forms a **cohesive story** (each slide's Goal and Transition should support the Narrative Arc). **Quality checklist (the model must self-check before finalizing)** * Titles are unique, concise (≤ 65 characters), and action-or insight-oriented. * Each slide has 3–6 bullets; no paragraph walls; numbers are specific where possible. * Visuals are concrete (chart/diagram names + variables/timeframes); tables are used only when necessary. * Terminology is defined once and used consistently; acronyms expanded on first use. * Transitions form an intelligible narrative; the story arc is obvious from titles alone. * No placeholders like "[TBD]" or "[insert]". If data is unknown, propose realistic figures and label as "example values". * All required headers and subsections are present, in the exact order above.
    ConnectorOAuth
  • Perform structural page operations on Canva designs: combine pages from multiple designs, insert pages, reorder pages, or delete entire pages. This tool can: 1. Create a new design by combining pages from one or more existing designs 2. Insert pages from one design into another existing design 3. Move or reorder pages within a design 4. Delete (remove) entire pages from a design Use this tool (NOT start-editing-transaction) when the user wants to: - Delete or remove one or more pages/slides from a design - Reorder or rearrange pages/slides within a design - Combine, merge, or stitch together multiple designs - Copy or insert pages from one design into another Do NOT use this tool for editing content within pages (text, images, etc.) — use start-editing-transaction for that. CRITICAL: You MUST ALWAYS ask the user for explicit confirmation before calling this tool, regardless of the operation type. Show them a summary of exactly what will change and ask "Would you like me to proceed?" Wait for their clear approval, then call this tool immediately. MANDATORY DELETE CONFIRMATION: If ANY operation in the list is a delete_pages operation, you MUST follow this protocol with NO exceptions — regardless of whether the pages are empty, have content, or any other condition: 1. Show a summary of ALL operations, marking each deletion as: "⚠️ Delete page(s) [X] — CANNOT BE UNDONE" 2. Tell the user: "To proceed, please type exactly: I approve the deletion" 3. ONLY call this tool if the user types the EXACT phrase "I approve the deletion" — do NOT accept any variation such as "yes", "ok", "approve", "I approve", "go ahead", "delete them", or any other paraphrase 4. If the user types anything other than the exact phrase, ask them again to type it exactly For insert_pages and move_pages only (no deletes), a simple "Would you like me to proceed?" confirmation is sufficient. Operations are applied sequentially. Page numbers are 1-based and evaluated at the time each operation runs. The tool automatically polls for job completion and returns the final result.
    Connector
    Destructive
    OAuth
  • Measured design CHANGE HISTORY for a live-decoded domain — the Decode Ledger. Token-level diffs between deep decodes over time: "radius 4px→8px", "primary hover #4032C8→#0A2540", "motion dominant 150ms→200ms", each dated. Use it to see how a product's design system is EVOLVING (no screenshot library can backfill this). site = a domain ("stripe.com") or product name. Returns first/last decode dates, decode_count and the dated change entries; empty history = measured, stable so far.
    ConnectorNo auth

Matching MCP Servers

  • A
    license
    A
    quality
    D
    maintenance
    Enables AI agents to manage routes on the Design Canvas infinite canvas app, including adding, removing, listing routes, and capturing screenshots of the canvas.
    4
    4
    4 npm
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Manages design tokens (colors, spacing, fonts) in a JSON file and enables agents to read, write, export, and detect drift between tokens and CSS via MCP.
    5
    MIT

Matching MCP Connectors

  • Design Feeds MCP.

  • Give your AI agents a design superpower. Generate, edit, and publish publication-grade decks, reports, landing pages, resumes, and marketing visuals directly within your agent workflow. Delivering frontier-level design quality at 3× the speed and 53× lower cost -from conversational prompt to live link or vector PDF in minutes.

  • Use this when the user wants Lemonvite's design engine to create the invitation artwork — because this assistant cannot produce images itself, or because the user asked for a Lemonvite design. Describe the look in design_brief (theme, colours, mood, motifs); the event date, time and venue are lettered onto the design automatically unless include_event_details is false. A reference_image from the conversation guides the engine's style. Each call spends one of the host's design generations (new accounts start with 5; every purchased publish credit adds 5) and REPLACES the current artwork (the previous design stays in the event's design history on the website), so confirm with the user before calling it. If this assistant already made an image in the conversation, attach it with invitation_image on lemonvite_update_invitation instead. Never call it merely because designs or themes are being discussed.
    Connector
    Destructive
    OAuth
  • Use this when the user wants a change to the invitation's CURRENT artwork rather than a new design — "make the sky a sunset", "change the balloons to gold", "remove the banner at the bottom". Lemonvite's design engine applies the request to the existing artwork and leaves everything else as it is. Put the user's request in edit_request in their own words; do not rewrite it into a design brief. Each call spends one of the host's design generations (same as lemonvite_generate_design) and REPLACES the current artwork (the previous version stays in the event's design history on the website), so confirm with the user before calling it. The invitation must already have artwork that is not a GIF and has no text or image layers added in the web editor (those are edited on the website); to create artwork from scratch use lemonvite_generate_design, and to attach an image this assistant made use invitation_image on lemonvite_update_invitation.
    Connector
    Destructive
    OAuth
  • Search Blueprint principles by free-text query and return the closest matches ranked by relevance. Use this to find principles related to a specific design challenge, failure mode, or keyword (e.g. 'reversibility', 'approval flow', 'delegation boundary'). Returns principle title, cluster, definition, rationale, and implementation heuristics. Prefer this over principles.list when you have a specific topic in mind rather than wanting all principles. NOTE: search currently covers the 10 agentic principles only; for the 8 experience-design laws or the 8 spec-quality laws use principles.list(lens='surface') / principles.list(lens='spec') until search spans all three lenses.
    ConnectorNo auth
  • Write the Design Document's Overview — the human-readable page a new team member reads first. WRITES DIRECTLY (no Inbox): it is a derived, clearly-labelled AI summary, not design truth, and the owner can clear or rewrite it in one click. HARD RULES, same as the in-app button: use ONLY facts stated in the design (call get_design_document with for_summary:true first); invent no mechanics, numbers or names; describe, never evaluate; write in the design's dominant language. Structure: `### What this is` · `### The core loop` · `### How the systems fit` (which system feeds which — the part a raw spec list cannot give) · `### Edges` (ONLY if the design states scope limits / open questions). 250-400 words, no top-level heading. Forge stamps the project version it was compiled from, so the owner is told when the design has moved past it.
    ConnectorNo auth
  • Search Blueprint principles by free-text query and return the closest matches ranked by relevance. Use this to find principles related to a specific design challenge, failure mode, or keyword (e.g. 'reversibility', 'approval flow', 'delegation boundary'). Returns principle title, cluster, definition, rationale, and implementation heuristics. Prefer this over principles.list when you have a specific topic in mind rather than wanting all principles. NOTE: search currently covers the 10 agentic principles only; for the 8 experience-design laws or the 8 spec-quality laws use principles.list(lens='surface') / principles.list(lens='spec') until search spans all three lenses.
    ConnectorNo auth
  • Get the Designesy design-system contract — the canonical tokens, motion, acoustic, takt, cadence, typography, components, and verification rules that define what the Designesy org considers legitimate design. Use this when you need the actual contract values (token names and values, motion timings, accessibility rules) to author, check, or bind a design. When NOT to use: for a pass/fail score of a live site, use designesy_score; for an agent-skill-format export, use designesy_skill_md. Read-only — cached ~24h server-side. Returns the full contract JSON, or a single section when "section" is provided. Pass section to get one slice (e.g. "motion" for just the motion tokens) instead of the full contract — saves tokens when you only need one dimension.
    ConnectorNo auth
  • What actually changed in the web's design systems lately — the nightly Drift Ledger feed. Mozaika re-measures ~100 of the most-referenced products every night and records a dated row per product even when nothing moved, so this is a real time series, not a guess: how many products held every token, which ones shipped a change that stuck (with before/after values and the date), and which design tokens move most often across the web. Use it to answer "does anyone actually redesign?", to ground a claim about design churn with a citable measurement, or to spot that a reference you rely on has moved. For one product, call get_design_drift(domain). Args: limit: how many confirmed changes to return (1-40, default 10). Free.
    ConnectorNo auth
  • Use when the user asks whether a board passes KiCad's own checks, or before trusting a design: returns the stored DRC (design rules, unconnected copper, schematic-vs-board parity) and ERC (electrical rules) results for the board's current version, with exact error and warning counts per category and paged example violations. These are KiCad's checks as the board's author configured them, so rules they waived were never evaluated and are listed separately. This is not a design review. If the checks have not been run for this version the result says so, and that is NOT the same as passing.
    ConnectorOAuth
  • Store a Roastify design JSON in your library (a commit in your GitHub repo). The browser courier reads a saved product's design and calls this to shuttle it up. On the way in, the design's fonts[] is REPAIRED — Roastify's own schema migration leaves a lossy fonts[] (a dropped family, a bad weight), so a stashed design would otherwise carry that damage; the repair rebuilds fonts[] from the families the text actually uses so it renders in its intended fonts. Only the load list changes; the text and its fonts are untouched. Inline images are de-duplicated. This does NOT touch Roastify.
    ConnectorNo auth
  • Convenience tool: generates a post with AI (postType 'CAROUSEL' by default, 'IMAGE' for a single-image post, or 'VIDEO' for a video), waits for it to finish, then creates a scheduled post that attaches the resulting design. May take 30-180 seconds (longer for a rendered video). templateId, brandId, presetId, and responseType are optional if saved via postnitro_set_defaults. The design that gets attached is the completed carousel's design ID (result.designId from the generation output) — NOT the generation job ID. You normally don't set designId; it's resolved automatically. Pass designId only to attach a pre-existing design instead of the freshly generated one. If scheduling fails after the carousel is already generated (e.g. an invalid platform-settings combination), this tool returns the generated designId so you can fix the inputs and retry with postnitro_create_scheduled_post — WITHOUT regenerating (which would burn credits again). Provide the scheduling fields (status, scheduledAt, selectedAccounts, captions, and any required per-platform settings) just as you would for postnitro_create_scheduled_post.
    ConnectorAPI key
  • Get a list of pages in a Canva design, such as a presentation. Each page includes its index and thumbnail. This tool doesn't work on designs that don't have pages (e.g. Canva docs). You must provide the design ID, which you can find using tools like `search-designs` or `list-folder-items`. You may also pass a full Canva design share URL directly (do not pre-extract just the ID) — any collaboration token embedded in the URL is needed to access a design shared via link and will be parsed and forwarded automatically. You can use 'offset' and 'limit' to paginate through the pages. Use `get-design` to find out the total number of pages, if needed.
    ConnectorOAuth
  • Get ranked, purchasable offers (price, ETA, preview image) for fabricating a physical item from a design file. process=fdm_print for 3D printing a model (STL/OBJ/PLY/3MF/AMF/STEP/IGES), process=cnc or process=sheetmetal for machined/bent metal parts (STEP, IGES, DXF), process=decal for stickers/decals from artwork (any common image or design file — PNG/JPG/HEIC/TIFF/GIF/BMP/WEBP/AVIF/SVG/PDF/AI/EPS/PSD/CDR, auto-converted). A .ufp file (UFP part container: the design plus saved spec/constraints in one) is accepted anywhere a design file is — its saved intent applies automatically and anything the user states now wins. If the user just drops a file and asks for a price, omit process — UFP routes it. Provide the design either as design_file (an image/file the user attached or you generated — preferred) or file_url (a public URL). REORDERS: if the user has a UFP part number (from a receipt email or a previous session, looks like UFP-… or part_…), pass it as part_number INSTEAD of any file — the stored design and spec are reused and re-shopped across all current vendors. Locked parts additionally require share_key (from the owner's share link). Returns offers across vendors like Google Flights returns flights.
    ConnectorNo auth
  • Returns AdCritter design guidance for an entity at a caller-chosen guidance level - screen experiences, API integration patterns, and design philosophy. The default ('full') returns step-by-step prescription (exact layouts, colors, copy text, column orders). Request 'patterns' for balanced hints including common design patterns with softened vocabulary. Request 'facts' if you have strong visual-design instincts and just want API integration bindings (or call adcritter_get_api_reference and adcritter_get_usage_guide directly and skip this tool). Guidance is format-agnostic - it describes outcomes and integration, never prescribes frameworks or architecture. Available entities: ad, advertiser, audience, authentication, blueprint, campaign, geo, media-asset, plan, report, settings.
    ConnectorNo auth
  • Interactive single-site design-conditions explorer. Returns full ASHRAE design conditions + diurnal chart for the requested scenario. In MCP Apps-capable hosts (Claude Desktop, ChatGPT, VS Code, Goose), the response renders as a widget with sliders for SSP / year / percentile / UHI — dragging a slider re-calls this tool live. Use when a user wants to interactively tune a single site. For multi-site comparison, use analyze_weather(urls=[...]) instead. Defaults to present-day TMY (no morph) — pass ssp+year for future scenarios. P75 default percentile is design-realistic; P50 underestimates the tail. No auth required.
    ConnectorNo auth
  • Overlay the current or any given planetary positions on a natal Human Design bodygraph to see which channels the transit temporarily completes. Returns the 13 transiting body activations with gate and line, the channels the transit completes beyond the natal definition split into personal channels where the transit supplies the partner gate of a natal gate and educational channels where the transit supplies both gates, the natally open centers those channels temporarily define, and a short factual summary. A transit is a single moment, so there is no Design side. When date and time are omitted the overlay is computed for now in UTC. Built for daily Human Design apps, transit widgets, and notification tools.
    ConnectorNo auth