Growaify — Autonomous Commerce for AI Agents
RemoteAbout Growaify — Autonomous Commerce for AI Agents
Growaify is an MCP server for an autonomous commerce platform, aimed at AI agents that need to find services and transact. It supports capability discovery, binding quotes, orders, payment verification, and deliverable checksums.
Key features
- 01Discover services by requirements
- 02Create binding service quotes
- 03Place idempotent orders
- 04Track order status and deliverables
- 05Inspect trust and SLA information
Use cases
- 01Find a service matching agent requirements
- 02Quote and purchase a service autonomously
- 03Track fulfillment and verify deliverables
MCP support
Exposes service discovery and commerce tools to MCP clients. Discovery works without an API key; quoting, purchasing, tracking, and trust queries require an X-API-Key.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://growaify.com/mcpclaude mcp add --transport http com-growaify https://growaify.com/mcp{"mcpServers":{"com-growaify":{"type":"http","url":"https://growaify.com/mcp"}}}Open in Cursor{"servers":{"com-growaify":{"type":"http","url":"https://growaify.com/mcp"}}}Open in VS Code{"mcpServers":{"com-growaify":{"type":"http","url":"https://growaify.com/mcp"}}}{"mcpServers":{"com-growaify":{"serverUrl":"https://growaify.com/mcp"}}}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.
https://growaify.com/mcpAuth requiredTools
7| Parameter | Type | Required | Description |
|---|---|---|---|
| required_capabilities | array | Yes | List of capability keywords to match, e.g. ['whatsapp', 'booking', 'multilingual', 'automation'] |
Details
From the project READMEGrowaify MCP Server
Official MCP (Model Context Protocol) server for the Growaify autonomous commerce platform.
This server implements the Growaify Protocol — the open spec, JSON schemas, conformance suite, and Agent/Provider SDKs live there. Verify any deployment:
python conformance/run.py https://growaify.com
Growaify lets AI agents discover services, negotiate binding quotes, place idempotent orders, pay, and receive cryptographically verified deliverables — fully autonomously.
What you can do with this server
| Tool | Description |
|---|---|
discover_capabilities | Match your requirements (e.g. ["whatsapp", "booking"]) against available services |
create_binding_quote | Get a deterministic, binding quote with agent pricing |
purchase_service | Place a state-machine order with verified payment rails |
track_order_telemetry | Track order status, progress (0–100%), and deliverables |
query_trust_and_sla | Inspect checksums, refund policies, and trust metadata |
Available services
| Service | Agent price | What you get |
|---|---|---|
| Smart Consultation | $1 | Tailored written consultation (immigration, legal, work, study) |
| Autonomous AI Task Worker | $15 | Finished written work: descriptions, replies, translations |
| AI Website + Booking | $69 | SEO-ready website with self-service booking |
| n8n / AI Automation | $69 | Custom n8n workflow, built, tested, deployed |
| AI WhatsApp Receptionist | $39 | 24/7 AI receptionist provisioning |
Installation
Via Smithery (recommended)
npx -y @smithery/cli install @habar/growaify --client claude
Claude Desktop
Add to claude_desktop_config.json (Settings → Developer → Edit Config):
{
"mcpServers": {
"growaify": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://growaify.com/mcp", "--header", "X-API-Key:YOUR_API_KEY"]
}
}
}
Cursor
Add to .cursor/mcp.json in your project root (or via Settings → MCP):
{
"mcpServers": {
"growaify": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://growaify.com/mcp", "--header", "X-API-Key:YOUR_API_KEY"]
}
}
}
Windsurf
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"growaify": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://growaify.com/mcp", "--header", "X-API-Key:YOUR_API_KEY"]
}
}
}
Discovery is open —
initialize,tools/list,ping, anddiscover_capabilitieswork with no API key. Commerce tools (create_binding_quote,purchase_service,track_order_telemetry,query_trust_and_sla) requireX-API-Key. You can connect without a key to inspect the surface; add one when you're ready to transact.
Example agent workflow
1. discover_capabilities(required_capabilities=["booking", "multilingual"])
2. create_binding_quote(service_id="website-booking")
3. purchase_service(quote_id="Q-...", email="[email protected]")
4. track_order_telemetry(order_id="ORD-...") → deliverables + checksum
Trust & verification
- Every deliverable ships with a SHA-256 checksum
- Orders are idempotent and enforced by a strict state machine
- Payments verified via PayPal NCP (webhook or operator secret) — never client assertion; x402 USDC rail deferred until on-chain verification
- Agent Card: https://growaify.com/.well-known/agent.json
- Trust portal: https://growaify.com/trust.html
- Live trust metrics: https://growaify.com/api/v1/trust (computed from real order records)
Links
- Website: https://growaify.com
- Protocol spec + SDKs + conformance suite: https://github.com/h-abar/growaify-protocol
- Agent Card: https://growaify.com/.well-known/agent.json
- OpenAPI spec: https://growaify.com/openapi.json
- Service catalog: https://growaify.com/catalog.json
- Agent SDK (Python):
sdk/agent/growaify_agent.py - Provider SDK (Python):
sdk/provider/growaify_provider.py - Live sandbox: https://growaify.com/sandbox.html
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.