Spree Commerce: open-source B2B and marketplace ecommerce
Open-source B2B and marketplace ecommerce; new stores include an MCP server for AI agents.
Description from the maker (original English)
Discover AgentBodega paid data tools, contracts, and x402/L402 HTTP payment handoff metadata.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
AGENTBODEGA_BASE_URLYou need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"agentbodega": {
"command": "npx",
"args": [
"-y",
"@agentbodega/mcp"
],
"env": {
"AGENTBODEGA_BASE_URL": "your-value"
}
}
}
}Run this in your terminal
claude mcp add agentbodega --env AGENTBODEGA_BASE_URL=your-value -- npx -y @agentbodega/mcpFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"agentbodega": {
"command": "npx",
"args": [
"-y",
"@agentbodega/mcp"
],
"env": {
"AGENTBODEGA_BASE_URL": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"agentbodega": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@agentbodega/mcp"
],
"env": {
"AGENTBODEGA_BASE_URL": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
AGENTBODEGA_BASE_URL envThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 9, 2026
The registry name was verified with the GitHub account agentbodegastore, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.1.7) reached the registry 4 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: Spree Commerce: open-source B2B and marketplace ecommerce, Stripe MCP, MCP Cn Commerce
Servers in the same category from other makers, sorted by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Open-source B2B and marketplace ecommerce; new stores include an MCP server for AI agents.
Stripe’s official server lets AI view and manage customers, products, payments and invoices. Connect to Stripe’s cloud and sign in with OAuth.
8 read-only MCP platform entries; support is operation-specific; merchant live acceptance pending
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Give agents a live menu of paid, x402-ready tools from AgentBodega.
This MCP server lets agents discover AgentBodega endpoints, compare prices, plan the cheapest useful route for a task, inspect required inputs and response formats, and generate ready-to-run x402 HTTP calls. Agents get the buying instructions for each resource without guessing schemas or scraping docs.
This public repository contains only the AgentBodega MCP package. The hosted AgentBodega API runs separately at agentbodega.store.
The MCP server does not execute paid calls. It returns the endpoint contract, example request, payment requirements, and snippets an agent can run against the hosted API. L402 is exposed as an additional discovery and payment-handoff surface; agents should treat it as discovery-only unless the live L402 document reports a configured issuer.
npx @agentbodega/mcp
Remote MCP clients that support Streamable HTTP can connect directly to:
https://agentbodega.store/mcp
SSE endpoint:
https://agentbodega.store/mcp/sse
Optional environment:
AGENTBODEGA_BASE_URL=https://agentbodega.store
Standalone agent skill:
curl -sS https://raw.githubusercontent.com/agentbodegastore/agentbodega/main/agent-skills/agentbodega/SKILL.md
This package intentionally uses outbound HTTPS requests at runtime to read AgentBodega's live catalog, x402 discovery document, L402 discovery document, and OpenAPI contract. It does not run install scripts, spawn shells, bundle dependencies, or execute paid calls. By default it connects to https://agentbodega.store.
{
"mcpServers": { "agentbodega": { "command": "npx", "args": ["-y", "@agentbodega/mcp"] } } }
agentbodega_plan_task - use first when an agent has a plain-language task and wants AgentBodega to choose the cheapest useful route. It calls the free /api/plan planner and returns a recommended endpoint, alternatives, required inputs, examples, and x402 handoff notes. It never executes paid calls.agentbodega_search_catalog - use first to find the right paid endpoint. It searches the live directory by text, department/category/tag, and maximum USD price, then returns endpoint summaries with required inputs and example requests. It never executes paid calls.agentbodega_get_endpoint - use after search when you know an endpoint key, path, title, or full URL. It returns the full contract: method, URL, price, required inputs, schemas, example request, output example, and long description. It does not call the endpoint.agentbodega_call_snippet - use after selecting an endpoint to generate ready-to-edit curl and JavaScript requests with an X-PAYMENT placeholder and x402 verification notes. It does not fetch a challenge, pay, or execute.agentbodega_payment_guide - use when an agent needs the AgentBodega payment model before making paid HTTP calls. It explains x402 discovery, L402 handoff status, settlement, blockchain-only balance policy, and optional challenge curl.agentbodega://catalog - compact live catalog.agentbodega://x402 - live x402 discovery document.agentbodega://l402 - live L402 discovery document.agentbodega://openapi - live OpenAPI document.npm install
npm test