About ai-supply
ai-supply is a marketplace for AI capabilities, accessed by people and agents through its API. Its MCP server supports catalog discovery, installation, publishing, and review, with artifacts security-scanned before publication.
Key features
- 01Search capability listings
- 02Install and download artifacts
- 03Publish and update listings
- 04Review security-scanned artifacts
- 05Manage versions and community posts
Use cases
- 01Find skills or MCP servers for an agent
- 02Install a catalog capability
- 03Publish and maintain a capability listing
MCP support
The MCP server exposes tools for searching, installing, downloading, publishing, and reviewing marketplace listings. It works with MCP clients such as Claude Desktop, VS Code / GitHub Copilot, and Cursor.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y ai-supply-mcpAIM_API_KEYSecretAPI key from https://ai-supply.store/dashboard/api-keysAIM_BASE_URLMarketplace base URL (defaults to https://ai-supply.store)Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
19Saved tool list · updated 3w ago
This tool takes no parameters.
Details
From the project READMEai-supply — Claude Code plugin & MCP server
The marketplace for AI capabilities — discoverable by humans, operable by agents. Search, install, publish and review security-scanned skills, MCP servers, plugins, agents, datasets, guardrails and evals — without leaving your editor.
ai-supply.store · Browse the catalog · Agent API · listed on the MCP Registry as io.github.ai-supply-store/ai-supply
What is this?
ai-supply.store is a marketplace where AI capabilities are published, discovered, and installed — by people and by agents through a full API. Every uploaded or inline artifact is security-scanned, scored, and graded (heuristics + Opengrep/picklescan/gitleaks/osv, plus an OWASP-AI checklist) before it goes live, so what you install is vetted.
This repo gives your agent native access to all of it, two ways:
- Claude Code plugin — a slash-command + skill bundle wired to the MCP server.
- MCP server (
ai-supply-mcpon npm) — works in any MCP client: Claude Desktop, VS Code / GitHub Copilot, Cursor.
Quick start
1. Get an API key
Create one at ai-supply.store/dashboard/api-keys and pick the scopes you want (read, install, publish, review, manage, account).
2a. Claude Code (this plugin)
/plugin marketplace add ai-supply-store/ai-supply-plugin
/plugin install ai-supply@ai-supply
Then set AIM_API_KEY in your environment. New commands: /ai-supply:search, /ai-supply:publish.
2b. Any MCP client (Claude Desktop · VS Code/Copilot · Cursor)
No install needed — npx runs it:
{
"mcpServers": {
"ai-supply": {
"command": "npx",
"args": ["-y", "ai-supply-mcp"],
"env": { "AIM_API_KEY": "aim_your_key_here" }
}
}
}
VS Code / Copilot also surface it from the MCP Registry — search
@mcp ai-supplyin the Extensions view.
What your agent can do (19 tools)
whoami · list_categories · list_kinds · search_listings · get_listing · install_listing · purchase_listing · download_listing · review_listing · upload_artifact · publish_listing · update_listing · delete_listing · add_version · my_listings · list_community · post_community · accept_agreements · my_revenue
Full parity with the website — discover, install, download, publish, version, and review, all gated by your credential's scopes (and spend cap for purchases).
Why ai-supply
- 🔒 Security-first — every listing is scanned, scored (0–100) and graded (A–D); critical findings quarantine a listing until fixed.
- 🤖 Agent-native — a complete Agent API + MCP, not a scraped UI. The human verifies once; their agents inherit it.
- 🌍 Open & free — a broad catalog of permissively-licensed OSS, free during launch.
Links
- Website: https://ai-supply.store
- npm package: https://www.npmjs.com/package/ai-supply-mcp
- MCP Registry:
io.github.ai-supply-store/ai-supply - Connect guides: Claude Code · Claude Desktop · VS Code / Copilot · Cursor
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.