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.
/plugin marketplace add markifact/markifact-mcpnpx agentmods add plugins/markifact/markifact-mcp/marketplacegit clone --depth 1 https://github.com/markifact/markifact-mcpGrade A, and why
markifact 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 yesterday.
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
{
"$schema": "https://json.schemastore.org/claude-code-marketplace.json",
"name": "markifact",
"description": "Run Google Ads, Meta Ads, GA4, Shopify, and 20+ more platforms from Claude. 1000+ operations with human-in-the-loop on every write.",
"owner": {
"name": "Markifact",
"email": "[email protected]"
},
"metadata": {
"pluginRoot": ".",
"description": "Run Google Ads, Meta Ads, GA4, Shopify, and 20+ more platforms from Claude. 1000+ operations with human-in-the-loop on every write."
},
"plugins": [
{
"name": "markifact",
"source": "./",
"version": "1.0.2",
"description": "Production performance marketing automation for Claude. Audit accounts, launch campaigns, rotate creative, and diagnose underperformers across Google Ads, Meta Ads, GA4, Shopify, HubSpot, and 20+ more. Approval-gated writes.",
"homepage": "https://www.markifact.com",
"repository": "https://github.com/markifact/markifact-mcp",
"license": "MIT",
"category": "marketing",
"tags": ["mcp", "claude-code", "claude-code-plugin", "marketing", "google-ads", "meta-ads", "facebook-ads", "ga4", "google-analytics", "dv360", "shopify", "hubspot", "linkedin-ads", "tiktok-ads", "marketing-automation", "performance-marketing", "ad-management", "media-buying", "agencies"],
"author": {
"name": "Markifact",
"email": "[email protected]"
}
}
]
}
What ships with it
2 files beside marketplace.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.
- yesterday First seen · 31 lines scan A 9c1d1899b05b
markifact is a plugin published in the GitHub repository markifact/markifact-mcp (48 stars, last pushed 13d 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 2026-08-30.
Other plugins, from other repositories
claw-hwp
Single-plugin marketplace shipping claw-hwp — Korean Hangul Word Processor (.hwp / .hwpx) support for Claude.
claw-hwp
Read, create, and edit Korean Hangul Word Processor documents (.hwp / .hwpx) in Claude. Built on the rhwp WebAssembly viewer/editor — no Hancom Office, no LibreOffice, no Windows COM required.
neels-plugins
Plugin marketplace listing 3 plugins: digital-marketing-pro, contentforge, socialforge.
aurora-agent
The AURORA Agent in one plugin: the bioprism MCP server (264 tools) wired into every session, FIBER decision-context commands (compile / explain / compare / validate / verify), mission preflight, an ops-auditor subagent, and skills for setup, the FIBER workflow, missions, and SDK integration. Requires a built…
aurora-backend
Wires the AURORA Agent (bioprism) MCP server into Claude Code: 259 tools for decision-context compilation (FIBER), missions, evaluation, capability routing, and the autonomous-brain control plane. Requires a built aurora-agent checkout (AURORAAGENTROOT or /aurora-agent).
aurora-context
Drive the FIBER decision-context compiler from any project: compile, explain, compare against baselines, validate worlds, and verify certificates, with the 10-exit-code retryability matrix interpreted for you. Requires a built aurora-agent checkout.