Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/canvora/canvora-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/canvora/canvora-mcp/claude-plugin)<a href="https://agentmods.dev/plugins/canvora/canvora-mcp/claude-plugin"><img src="https://agentmods.dev/badge/plugins/canvora/canvora-mcp/claude-plugin/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/canvora/canvora-mcp/claude-plugin"><img src="https://agentmods.dev/badge/plugins/canvora/canvora-mcp/claude-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
canvora scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "canvora",
"displayName": "Canvora",
"version": "1.4.1",
"description": "Turn any idea, URL, or document into on-brand marketing visuals: posts, carousels, ads, and slides in 100+ formats and 150+ languages. Bundles the Canvora connector with 12 task skills (carousels, pitch decks, PDFs, ad sets, landing-page kits, localization).",
"author": {
"name": "Canvora",
"email": "[email protected]",
"url": "https://canvora.ai/"
},
"homepage": "https://canvora.ai/for-agents",
"repository": "https://github.com/canvora/canvora-mcp",
"license": "MIT",
"keywords": [
"design",
"marketing",
"social-media",
"carousel",
"presentation",
"branding",
"localization",
"visuals"
],
"icon": "./.claude-plugin/icon.png",
"documentationUrl": "https://canvora.ai/help/integrations/mcp-setup",
"supportUrl": "https://canvora.ai/support",
"privacyPolicyUrl": "https://canvora.ai/privacy",
"termsOfServiceUrl": "https://canvora.ai/terms"
}
What it installs
The manifest is a name and a version. 12 skills, 1 MCP server travel with it, and installing the plugin installs all of them — 779 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill canvora A 85 tokens
- Skill instagram-carousel A 57 tokens
- Skill multilingual-campaign A 75 tokens
- Skill pdf-document A 65 tokens
- Skill pitch-deck A 61 tokens
- Skill product-photo-visuals A 65 tokens
- Skill visual-refresh A 55 tokens
- Skill ad-campaign A 57 tokens
- Skill blog-promo-kit A 62 tokens
- Skill data-infographic A 63 tokens
- Skill landing-page-visuals A 69 tokens
- Skill linkedin-carousel A 65 tokens
- MCP server canvora A not measured
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 30 lines scan A 3c2f991eaaf2
canvora is a plugin published in the GitHub repository canvora/canvora-mcp (1 stars, last pushed 4d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-28.
Other plugins, from other repositories
langroid
Design patterns for the Langroid multi-agent LLM framework.
mem9
Persistent cloud memory for Claude Code. Auto-loads memories on session start, auto-saves on stop, with on-demand store/recall skills.
harness-platform
8 skills: Operate delegates, IaCM workspaces, cloud development environments, artifact registries, SBOMs, supply chain and pull requests.
jk
GitHub CLI-style interface for Jenkins controllers - create multibranch jobs, inspect config.xml, and manage runs, logs, artifacts, credentials, nodes, and queues.
watchgoose-monitoring
Audit cron and scheduled-job monitoring coverage, set up Watchgoose checks for one job or a batch, review monitoring health and triage missed runs.
claude-superskills marketplace
Plugin marketplace listing 1 plugin: claude-superskills.