mcpField
N
Nexbid

Nexbid

Remote
github.com/nexbid-devBusiness & Marketing0Updated 8w ago
Repository

About Nexbid

Nexbid is the reference implementation of Protocol Commerce, an open initiative for interoperable, auditable commerce protocols for AI agents. Its MCP integration lets compatible LLMs search, browse, and purchase products through a marketplace, with privacy-focused operation and formally verified core security properties.

Key features

  1. 01MCP-native product discovery and purchasing
  2. 02AdCP and AMDP protocol specifications
  3. 03TypeScript SDK and validators
  4. 04Browser tools through WebMCP
  5. 05Lean 4 proofs of core properties

Use cases

  1. 01Searching and browsing marketplace products with an MCP-compatible LLM
  2. 02Facilitating product purchases through an AI agent
  3. 03Building commerce integrations with the AdCP SDK

MCP support

Nexbid provides an MCP endpoint for compatible LLMs to search, browse, and purchase products through its marketplace. The repository also includes a WebMCP reference for exposing commerce tools to in-browser AI agents.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.nexbid.dev/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

19
ParameterTypeRequiredDescription
querystringYesNatural language product or recipe query
content_typeenumNoFilter by content type: product, recipe, or all (default)all | product | recipe | service
intentenumNoUser intent for the searchpurchase | compare | research | browse
budget_max_centsintegerNoMaximum budget in cents (e.g. 20000 for CHF 200)
budget_min_centsintegerNoMinimum budget in cents
currencyenumNoCurrency for budget filteringCHF | EUR | USD | GBP
geostringNoISO 3166-1 alpha-2 country code (default: CH)
categorystringNoFilter by product category
brandstringNoFilter by brand name
max_resultsintegerNoMaximum number of results (1-50, default: 10)
previous_queriesarrayNoPrevious queries in this search session for multi-turn refinement (oldest first, max 10). Example: ["running shoes", "waterproof only"]
agent_idstringNoAgent identifier — used for analytics-attribution (e.g. "claude-3.5", "gpt-4o", "perplexity"). Optional but strongly recommended so publishers/advertisers can see which AI agents drive their traffic.
session_idstringNoSession token to correlate multiple tool-calls from the same conversation. Optional. Useful for multi-turn analytics.

Details

From the project README

Protocol Commerce

The open infrastructure for agent-native commerce.

Protocol Commerce is an open initiative to create standardized, auditable, and interoperable protocols for AI agent-driven commerce. This repository contains the specification, SDKs, and technical manifesto.

Contents

DirectoryDescription
manifesto/Why open protocols matter for commerce — principles, landscape analysis, and rationale
adcp-spec/AdCP v0.1.0 — Agentic Discovery Commerce Protocol specification, JSON schemas, and examples
adcp-sdk-typescript/TypeScript SDK: types, validators, client, and scoring reference implementation
webmcp-reference/WebMCP browser integration: expose commerce tools to in-browser AI agents via navigator.modelContext
amdp-spec/AMDP v0.1.0 — Agent Mandate Discovery Protocol: cross-vertical authorization spec, JSON schemas, and example mandates
agentic-kit/Agentic Kit — the trust layer: building blocks for verifiable + auditable AI agents
lean-verification/Lean 4 formal verification — 47 theorems proving auction/budget/wallet/policy correctness, lake build-checkable

Quick Start

npm install @protocol-commerce/adcp-sdk
import { AdcpClient } from '@protocol-commerce/adcp-sdk';

const client = new AdcpClient({
  serverUrl: 'https://mcp.nexbid.dev',
  apiKey: 'your-api-key',
});

const results = await client.search({
  query: 'organic olive oil',
  intent: 'purchase',
  geo: 'CH',
});

The Problem

AI agents are becoming the primary interface for product discovery and purchase. The protocols powering this shift — OpenAI's ACP, Google's UCP — are proprietary and platform-controlled. Publishers have no representation. There is no open standard.

Protocol Commerce fills this gap.

Read the full Technical Manifesto →

Key Principles

  1. Open by Default — MIT-licensed, auditable, forkable
  2. Publisher Parity — Publishers are first-class protocol participants
  3. Privacy Native — Context signals, not user profiles
  4. Transparent Scoring — Public formula: score = 0.4×bid + 0.4×relevance + 0.2×quality

All 7 principles →

Reference Implementation: Nexbid

Nexbid is the production-grade reference implementation of Protocol Commerce, built by digital opua GmbH (CHE-435.289.702, Switzerland).

MetricStatus
MCP IntegrationNative — full commerce lifecycle
Formal VerificationLean 4 — core security properties proven
PrivacyCookie-free, Swiss-hosted, nDSG + GDPR compliant
AI ScoringMulti-provider, model-agnostic
PhaseProduction-grade closed beta
Connect Any LLM
{
  "mcpServers": {
    "nexbid": {
      "url": "https://mcp.nexbid.dev/mcp",
      "transport": "streamable-http"
    }
  }
}

Any MCP-compatible LLM (Claude, GPT-4, Gemini) can directly search, browse, and purchase products through the Nexbid marketplace.

Why Formal Verification?

Nexbid is the only commerce platform whose core security properties are mathematically proven in Lean 4 — not just tested, but proven correct for all possible inputs.

→ Technology details · How Nexbid compares

Sponsors

SponsorRole
NexbidInitiator, reference implementation, initial maintainer

License

MIT — Use it, fork it, build on it. No strings attached.

Links

Comments

Markdown supported

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.