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/ContentWriterco/Compabase-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/contentwriterco/compabase-mcp/claude-plugin)<a href="https://agentmods.dev/plugins/contentwriterco/compabase-mcp/claude-plugin"><img src="https://agentmods.dev/badge/plugins/contentwriterco/compabase-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/contentwriterco/compabase-mcp/claude-plugin"><img src="https://agentmods.dev/badge/plugins/contentwriterco/compabase-mcp/claude-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
compabase 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 7d 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": "compabase",
"version": "1.0.0",
"description": "Polish company data in Claude: 3M+ companies from KRS and CEIDG with financial statements, owners, public tenders and risk checks. Sign in with your Compabase account.",
"author": {
"name": "Content Writer LLC",
"email": "[email protected]",
"url": "https://compabase.com"
},
"homepage": "https://compabase.com/docs/mcp/",
"repository": "https://github.com/ContentWriterco/Compabase-MCP",
"license": "MIT",
"keywords": [
"poland",
"company-data",
"krs",
"kyb",
"due-diligence",
"financial-statements",
"public-procurement",
"mcp"
],
"privacyPolicyUrl": "https://compabase.com/privacy",
"supportUrl": "https://compabase.com/contact",
"termsOfServiceUrl": "https://compabase.com/terms",
"documentationUrl": "https://compabase.com/docs/mcp/connect/claude/"
}
What it installs
The manifest is a name and a version. 1 MCP server travel with it, and installing the plugin installs all of them. Each is measured on its own page, and each can be installed alone.
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.
- 7d ago First seen · 28 lines scan A 3445d392d78b
compabase is a plugin published in the GitHub repository ContentWriterco/Compabase-MCP (0 stars, last pushed 7d 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 2026-10-10.
Other plugins, from other repositories
scala
S.C.A.L.A. AI OS — Run your entire business from Claude. CRM, invoicing, bookings, SARA AI assistant, 20 industry verticals, 250M+ company database.
polar-skills
Official Polar skills for billing, subscriptions, and local development.
stripe-skills
Official Stripe skills for payments, billing, Connect, Apps, and API upgrades.
personal
Personal knowledge and finance automation — autonomous Obsidian vault management (PARA + LLM Wiki) and end-to-end corporate/personal tax preparation from Xero, bank statements, and Google Drive.
utopia-investments
Investments — due diligence, financial modeling, valuation, capital markets, fundraising decks, and quant pricing, plus the founder-side investor reading room. For funds team and fundraising.
llmquant-skills
Finance research, trading, risk, and portfolio Agent Skills grounded in LLMQuant Data. Bundles every llmquant- category skill under skills/.