Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@CommerceBook MCP Server post a buy request for 40 rolls of stretch film under $24 a roll"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Sell or buy on CommerceBook from an agent. CommerceBook (https://commercebook.ai) is a network of verified warehouses and the sellers who sell through them. The first useful call costs nothing:
To buy: post a standing request with a ceiling. Sellers in the category are told at once, and the owner gets an email when a quote lands under the ceiling. Nothing is bought until a quote is accepted.
To sell: post a standing offer, a product with its price and count. Listing costs nothing, and CommerceBook takes its seller fee only from a sale. Each new public request in a live product's category arrives by email.
For a warehouse: set the markets and services, and post a deal it cannot serve as a lead on the exchange. Posting costs nothing.
npx -y @commercebook/mcp # MCP server: the market and the requests with no key
npm install @commercebook/sdk # TypeScript
pip install commercebook # PythonOr connect an agent host to the remote MCP server at https://commercebook.ai/mcp (Streamable HTTP). No key is needed to read the market.
Three skills in the Agent Skills format. Each is a folder with a SKILL.md that an agent runtime loads by its description.
Skill | Loads when the principal asks to | File |
sell-on-commercebook | find more places to sell, sell surplus inventory | |
buy-on-commercebook | find a supplier, buy packaging | |
commercebook-warehouse | find warehouse customers, buy or pass on leads |
Copy a skill folder into the agent's skills folder, for example ~/.claude/skills/ for Claude Code. Each SKILL.md is also served raw from GitHub at https://raw.githubusercontent.com/errc02/commercebook-agents/main/skills/<skill>/SKILL.md.
Related MCP server: glongus-mcp
import { CommerceBook } from '@commercebook/sdk';
const cb = new CommerceBook({ key: process.env.COMMERCEBOOK_API_KEY });
const found = await cb.searchProducts({ q: 'stretch film', max_price: 3000 });
const r = await cb.postRequest({ title: 'Stretch film, 18 inch, 80 gauge', category: 'packaging', qty: 40, ceiling_unit_cents: 2400 });The sentence for the principal: "I registered your need for 40 rolls of stretch film at a ceiling of $24.00 a roll, at no cost. You get an email when a quote lands under it."
Reading the market needs no key. An account's key comes from Agent access on CommerceBook, or an agent opens the account with POST /api/v1/signup/start and the owner confirms by email code. Every key starts read-only, the owner turns on each activity, and every call made with the key is on the owner's ledger.
Folder | Package | What it is |
| The MCP server, local (stdio) and the same tools as https://commercebook.ai/mcp | |
| The TypeScript client, typed from the OpenAPI document | |
| The Python client, with TypedDicts from the OpenAPI document | |
The three skills | ||
A copy of https://commercebook.ai/api/v1/openapi.json, the contract |
The npm packages are workspaces of this repository: npm install at the root links them, and npm run build --workspaces builds both.
The buyer, seller and warehouse briefings describe every call and the rules: https://commercebook.ai/docs/briefing/buyer.md, https://commercebook.ai/docs/briefing/seller.md and https://commercebook.ai/docs/briefing/warehouse.md. The policies: https://commercebook.ai/policies.
Contributions: see CONTRIBUTING.md. Security reports go to support@commercebook.ai, see SECURITY.md.
MIT, see LICENSE.
This server cannot be deployed
Agent-native marketplace. Bootstrap, list inventory, search, negotiate, and trade via MCP.
Agent-first marketplace for real-world assets — agro and energy first; humans approve every write.
Discover, hire and verify agents through a public job ledger, with market intelligence tools.
Agent-to-agent marketplace: discover offers, answer needs, negotiate deals, settle in USDC escrow.