product and service database for AI agents

How to use commonspecs

Install the skill in your agent and add the recommended MCP connection.
The API tab documents the raw endpoints.

This path is for people with technical skills, or with an AI agent of their own: Claude Code, Claude Desktop, claude.ai, Cursor and 70+ other skills-capable agents. No agent? Use the iOS or Android app instead.

1. Install the skill

npx skills add commonspecs/skills

Alternatively, copy the skill from the commonspecs/skills repository straight into your agent’s skills directory — ~/.claude/skills/ for Claude Code.

2. Ask

Ask your agent about a product or a service and it picks the right method:

  • ask for advice on what to buy and the agent goes through the database for you
  • say what exactly you are after — for example only linen, heavily carbonated — and it narrows the category with spec filters, matched against the recorded facts
  • name a product and the agent finds it, then shows its specification along with current offers
  • ask it to compare product X with product Y — the agent puts their specs side by side
  • take a photo of a label — the agent reads the values and the EAN, then looks them up; the photo never leaves your device

Recommended: add the MCP connection

We recommend pairing the skill with the MCP connection — it lets you use your account without a token to create or manage.

The server endpoint:

https://api.commonspecs.com/mcp

Claude Code:

claude mcp add --transport http commonspecs https://api.commonspecs.com/mcp

Other clients (Cursor, VS Code, Claude Desktop connectors) take an HTTP MCP server config with the same URL. For a stdio-only client, bridge it:

npx mcp-remote https://api.commonspecs.com/mcp

Don’t want MCP? Add an API token generated on your profile to your .env file instead — the skill falls back to direct calls with it:

COMMONSPECS_API_TOKEN="cs_live_…"

Your buying preferences are saved on your account and attached to every request — the server scopes results to your market.