Skip to main content
Glama

Canva

by com.canva.mcp
OverviewDiscussionsAdmin

Import Design From Public HTTPS URL

import-design-from-url

Convert content at a public URL into a new Canva design.

Use to turn a publicly hosted PDF, slide deck (PowerPoint or Keynote), document (Word, Pages, or Markdown), spreadsheet (Excel, CSV, or Numbers), webpage or HTML, or design file (Photoshop or Illustrator) into a Canva design.

Only call with a public HTTPS URL. Do not use for local, private, or agent-generated files, or to break a flat PNG, JPEG, or WEBP into separately editable layers.

Each call creates one design and returns its design_id.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesPublic HTTPS URL for the source to convert. Does not accept Canva design URLs, OpenAI file URLs, local paths, private files, or agent-generated files. For static HTML, each top-level Canva page element must have data-document-role="page" and page elements cannot be nested. Use optional data-label and data-speaker-notes attributes for page titles and presenter notes. Do not add page annotations to interactive HTML.
nameYesName for the new Canva design.
user_intentNoMandatory description of what the user is trying to accomplish with this tool call. This should always be provided by LLM clients. Please keep it concise (255 characters or less recommended).
intended_design_typeNoRequested Canva output format. Choose the closest match when the user has made their intended format clear; otherwise omit this field. Use "other" only when the intended format is clear but is not listed.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / intended_design_type / description
      Previous value: -"The design type the user appears to want to create from this URL. Choose the closest match based on the user request and the URL. If unclear, omit this field. Use other only when the intended design type is clear but none of the listed options fit."New value: +"Requested Canva output format. Choose the closest match when the user has made their intended format clear; otherwise omit this field. Use \"other\" only when the intended format is clear but is not listed."
    • changedInput schema / properties / name / description
      Previous value: -"Name for the new design"New value: +"Name for the new Canva design."
    • changedInput schema / properties / url / description
      Previous value: -"Public HTTPS URL to the file to import. MUST START WITH https://. Examples: https://example.com/file.pdf, https://example.com/site.zip, https://raw.githubusercontent.com/user/repo/main/design.zip CRITICAL: If user input is a local path (starts with /, C:\\, file://, or mentions Downloads/Documents/Desktop), DO NOT USE THIS TOOL. If it looks like a Canva design URL, DO NOT call this tool."New value: +"Public HTTPS URL for the source to convert. Does not accept Canva design URLs, OpenAI file URLs, local paths, private files, or agent-generated files. For static HTML, each top-level Canva page element must have data-document-role=\"page\" and page elements cannot be nested. Use optional data-label and data-speaker-notes attributes for page titles and presenter notes. Do not add page annotations to interactive HTML."
  2. First observed

TDQS

A4.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate readOnlyHint=false and destructiveHint=false, but do not explain creation semantics. The description adds that 'Each call creates one design and returns its design_id,' which is valuable behavioral context. It also discloses the limitation regarding flat images, helping the agent set expectations. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core action, followed by supported formats, exclusions, and return behavior. Each sentence serves a purpose: scope, eligibility, counter-indications, and outcome. No redundancy or fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a creation tool with no output schema, the description covers what the agent needs: supported inputs, key constraints, creation count, and return value (design_id). The input schema supplements with detailed URL and format parameters. Together the definition is complete enough to invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all four parameters, including the detailed URL constraints and enum options. The description itself adds little param-specific detail, but it does reinforce the public-URL restriction. Baseline 3 applies because the schema carries the semantic burden.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Begins with a specific verb and resource: 'Convert content at a public URL into a new Canva design.' It names the exact domain (public HTTPS sources) and the artifact (a new Canva design), and enumerates supported file types. This clearly separates it from sibling creation tools like generate-design or create-design-from-brand-template, which use different sources.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use ('Use to turn a publicly hosted...') and when not to ('Do not use for local, private, or agent-generated files, or to break a flat PNG, JPEG, or WEBP'). This gives the agent unambiguous selection criteria without needing to infer from the schema. The 'Only call with a public HTTPS URL' constraint is direct and actionable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Canva toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources