Developer integration paths

Capture purchase intent inside any AI you ship

SellToAI is the merchant-side bridge into the AI surfaces buyers already trust. Drop the SDK / SKILL / MCP / OpenAPI snippet into your agent host below, and SellToAI will translate every shopping turn into a structured intent your store can answer with real proposals — not links. Use the Developer Console when production `/v1/*` calls need a Bearer API key.

See it work Run the live shopper demo first Type one shopper need, watch /v1/recommend return ranked PCD cards with attribution links. Open /try → Get a key Create a Bearer API key in the console Register, verify your invite, and mint a key to call /v1/* from production. Open /developers → Read the contract Browse OpenAPI / Agent Card / SKILL All four protocol surfaces in one page — pick the one your stack already speaks. Open /reference →

Need to install or configure a host first? Start with the official docs:

OpenClaw install Hermes install Cursor download Claude Code setup Codex CLI docs Claude Desktop MCP ChatGPT Actions Gemini function calling

Choose the fastest path for your channel

Most teams only need one surface to start. Pick the host or protocol you already use, copy the first block, then drop into the deeper workflow only if you need merchant-side negotiation.

Skill hosts

Best for Cursor and Claude Code skills. OpenClaw shares the Local agent hosts section with Hermes — install snippets are first on each card.

Open skill hosts

OpenAPI apps

Best for ChatGPT and Gemini. Paste one manifest URL and start calling the gateway with hosted tools.

Open OpenAPI apps

MCP hosts

Best for Codex and Claude Desktop. Add a single `mcpServers` entry and call SellToAI as a local tool.

Open MCP setup

Hermes / A2A clients

Hermes lives under Local agent hosts next to OpenClaw. Need raw REST only? Jump to Anything else after you finish the Hermes card.

Open Hermes / A2A flow

Universal entrypoints

These URLs are the shared front doors behind every channel-specific guide on this page.

OpenAPI manifest

https://selltoai.ai/openapi.json

A2A Agent Card

https://selltoai.ai/.well-known/agent-card.json

Skill installer

https://selltoai.ai/skills/install.sh

REST base

https://selltoai.ai/v1

Local agent hosts · OpenClaw & Hermes

OpenClaw

Drop the SellToAI Shop skill into OpenClaw with a single curl command. Works in any new chat.

Protocols

SKILL

Copy-ready snippets

Install OpenClaw first (one-liner)

Official installer from openclaw.ai. Skip if `openclaw --version` already works.

curl -fsSL https://openclaw.ai/install.sh | bash

# Already have Node 22+? Alternative:
# npm install -g openclaw@latest

Install the skill (one-liner)

Installs SKILL.md into every supported agent skills folder. `curl … | bash` works from fish, zsh, or bash.

curl -fsSL https://selltoai.ai/skills/install.sh | bash

Or copy the skill manually

If your team forbids piping curl into bash, just save the file under your skills directory.

mkdir -p ~/.openclaw/skills/moras-shop && \
  curl -fsSL https://selltoai.ai/skills/moras-shop/SKILL.md \
  -o ~/.openclaw/skills/moras-shop/SKILL.md

Verify it works

Open a new OpenClaw chat and try the prompt below. It names the skill once to force the first activation; follow-up shopping prompts should auto-activate.

use the moras-shop skill: recommend a small birthday gift for a 5 year old kid

Hermes

Unlike OpenClaw (a SKILL.md file), Hermes wires SellToAI through A2A: register the Agent Card URL once, then call message/send with skill_id from that JSON—or skip A2A and use GET /v1/recommend like any REST client.

Protocols

A2ASSE

Copy-ready snippets

Install Hermes Agent first (one-liner)

Official installer from NousResearch. Skip if `hermes --version` already works. Windows: use WSL2.

curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash

Enable SellToAI on Hermes (no SKILL file)

The curl blocks below are smoke tests. In Hermes, point your runtime at the Agent Card URL so it learns skill ids; then your graph/CLI issues the same JSON-RPC your curl would.

1) Register — In Hermes (or your CrewAI / AutoGen / LangGraph setup), add the Agent Card URL below as the Moras agent discovery endpoint. Exact setting name is in NousResearch docs; it is not a file path like ~/.openclaw/skills/.

2) Discover — Hermes fetches the JSON; shopping uses skill_id "recommend_products" (see "skills" in that file).

3) Invoke — POST https://selltoai.ai/a2a with jsonrpc "message/send" and message.metadata.skill_id (example in the next block). For async tasks, poll SSE as in the final block.

Shortcut — Same gateway: GET https://selltoai.ai/v1/recommend?intent=...&channel=hermes (no JSON-RPC).

Agent Card URL (discovery)

https://selltoai.ai/.well-known/agent-card.json

Start an async recommendation task (JSON-RPC 2.0)

This runs the same recommend_products flow as /v1/recommend, but via the A2A task runtime.

curl -X POST https://selltoai.ai/a2a \
  -H "Content-Type: application/json" \
  -H "X-Channel: hermes" \
  -d '{
    "jsonrpc":"2.0",
    "id":"req-1",
    "method":"message/send",
    "params":{
      "message":{
        "role":"user",
        "parts":[{"kind":"text","text":"recommend a small birthday gift for a 5 year old kid"}],
        "metadata":{"skill_id":"recommend_products","async":true,"limit":3}
      }
    }
  }'

Stream task events over SSE

Replace TASK_ID with the task id returned by message/send.

curl -N https://selltoai.ai/a2a/tasks/TASK_ID/events

Skill Hosts

Cursor

Cursor reads agent skills from ~/.cursor/skills. Same one-liner as OpenClaw.

Protocols

SKILL

Copy-ready snippets

Install the skill

Same script as OpenClaw; installs into all supported skill directories.

curl -fsSL https://selltoai.ai/skills/install.sh | bash

Try it from the chat

> use the moras-shop skill — find me a portable blender

Claude Code

Claude Code skills live in ~/.claude/skills. Same installer, different target dir.

Protocols

SKILL

Copy-ready snippets

Install the skill

Same script as OpenClaw; installs into all supported skill directories.

curl -fsSL https://selltoai.ai/skills/install.sh | bash

Try it

recommend trending pet products on TikTok Shop

OpenAPI Apps

ChatGPT (Apps SDK / Custom GPT)

ChatGPT consumes our OpenAPI 3.0 manifest. Paste the URL in your Custom GPT or Apps SDK config, then configure Bearer auth.

Protocols

OPENAPIREST

Copy-ready snippets

OpenAPI manifest URL

In ChatGPT → Configure → Actions → Import from URL.

https://selltoai.ai/openapi.json

Authentication

Use Bearer auth for /v1/* calls. Create a key in the Developers console, then configure it in your Action auth settings.

Authentication type: API Key
Auth type: Bearer
Header: Authorization: Bearer MA2A.xxx

Suggested system instructions

When the user asks for a product recommendation, gift idea, or "what should I buy",
call recommendProducts with the user's intent paraphrased into one short English line.
Return each card's cta.primary.url verbatim — never rewrite the buy link.

Gemini Extension

Gemini Extensions / Gems also speak OpenAPI. Same manifest URL; configure Bearer auth for protected /v1/* calls.

Protocols

OPENAPIREST

Copy-ready snippets

OpenAPI manifest URL

https://selltoai.ai/openapi.json

Test in Gemini AI Studio

Tools → Function Calling → Import OpenAPI → paste the URL.

recommend a small birthday gift for a 5 year old

MCP Hosts

Codex / Claude Desktop (MCP)

Codex and Claude Desktop can spawn our MCP wrapper as a stdio child process. Add this to your MCP config.

Protocols

MCP

Copy-ready snippets

mcpServers entry

Add into ~/.codex/config.json or claude_desktop_config.json under "mcpServers".

{
  "mcpServers": {
    "moras-shop": {
      "command": "npx",
      "args": ["-y", "moras-a2a-mcp@latest"],
      "env": {
        "MORAS_A2A_BASE_URL": "https://selltoai.ai",
        "MORAS_A2A_CHANNEL": "codex"
      }
    }
  }
}

Or run from the cloned repo

Use your own deployment path instead of a public clone URL.

cd /path/to/moras-A2A && npm install
MORAS_A2A_BASE_URL=https://selltoai.ai node bin/mcp.js

Raw Workflows

Anything else (raw REST)

Use the REST layer directly for both buyer-side discovery and merchant-side exchange objects.

Protocols

RESTA2A

Copy-ready snippets

Recommend by intent

curl 'https://selltoai.ai/v1/recommend?intent=birthday%20gift%20for%205%20year%20old&limit=3' \
  -H 'Authorization: Bearer MA2A.xxx' \
  -H 'X-Channel: my-agent'

Create a developer account

curl -X POST https://selltoai.ai/v1/developers/register \
  -H 'Content-Type: application/json' \
  -d '{"display_name":"My Agent","contact_email":"[email protected]","password":"change-me-now","company":"Example Labs"}'

Inspect your keys and logs

curl https://selltoai.ai/v1/developers/me \
  -H 'Authorization: Bearer moras_dev_xxx'

curl 'https://selltoai.ai/v1/developers/logs?limit=20' \
  -H 'Authorization: Bearer moras_dev_xxx'

Create a first-class intent

curl -X POST https://selltoai.ai/v1/intents \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer MA2A.xxx' \
  -H 'X-Channel: my-agent' \
  -d '{"raw_query":"birthday gift for a 5 year old","region":"US","audience":"parent","budget_range":{"max":35,"currency":"USD"}}'

Save the returned registration_token. You need it later for heartbeat, updates, and proposal submission.

curl -X POST https://selltoai.ai/v1/merchant/register \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer MA2A.xxx' \
  -H 'X-Channel: merchant-onboarding' \
  -d '{"merchant_id":"mch_demo","agent_endpoint":"https://example.com/webhook","subscription_tags":["outdoor"],"capabilities":["stock_check"],"regions":["US"]}'

Use this general registry for payment, logistics, creator, demand-side, merchant, or SellToAI-core agents.

curl -X POST https://selltoai.ai/v1/agents/register \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer MA2A.xxx' \
  -H 'X-Channel: agent-registry' \
  -d '{"agent_id":"payment_demo","agent_type":"payment","endpoint":"https://example.com/a2a","protocols":["a2a-jsonrpc","webhook"],"auth_methods":["intent_mandate"],"capability_profile":{"payment":{"create_checkout":true}}}'

List registered Commerce Agents

curl 'https://selltoai.ai/v1/agents?agent_type=payment&status=active' \
  -H 'Authorization: Bearer MA2A.xxx'

Submit a merchant proposal

Requires the X-Merchant-Token returned from registration.

curl -X POST https://selltoai.ai/v1/proposals \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer MA2A.xxx' \
  -H 'X-Merchant-Token: mrt_xxx' \
  -d '{"merchant_agent_id":"mch_demo","intent_id":"int_xxx","product_id":"123456789","offer_title":"Trail-ready lantern bundle","price":29.99,"inventory_status":"in_stock","shipping_commitment":{"eta_days":3}}'

Create a match session from intent + proposals

curl -X POST https://selltoai.ai/v1/match \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer MA2A.xxx' \
  -H 'X-Channel: my-agent' \
  -d '{"intent_id":"int_xxx","proposal_ids":["prp_xxx","prp_yyy"],"limit":3}'

Run a Commerce Runtime loop

Creates a linked Intent, Proposal, Match Session, Match Token, and runtime_trace in one auditable call.

curl -X POST https://selltoai.ai/v1/commerce-runtime \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer ***' \
  -H 'X-Channel: my-agent' \
  -d '{"runtime_session":{"entry_agent_id":"my-agent","mode":"assisted_commerce"},"commerce_budget":{"max_merchant_queries":3,"require_user_confirmation_before_payment":true},"skill_refs":["enterprise_gifting_sop"],"intent":{"raw_query":"birthday gift for a 5 year old","region":"US","audience":"parent"},"proposal":{"merchant_agent_id":"moras-core","product_id":"demo-gift","offer_title":"Curated birthday gift bundle","price":29.99}}'

Accept a ranked proposal and mint the match token

Turns buyer-agent intent into a signed intent → merchant proposal → MatchToken → confirmation transaction plan. This is transaction protocol, not sponsored placement.

curl -X POST https://selltoai.ai/v1/agentic-checkout \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer ***' \
  -H 'X-Channel: my-agent' \
  -d '{"buyer_agent_id":"gpt-shopper-agent","raw_query":"birthday gift for a 3 year old nephew under $40","region":"US","commerce_budget":{"max":40,"currency":"USD"},"proposal":{"merchant_agent_id":"toy-merchant-agent","product_id":101,"title":"Montessori Wooden Animal Puzzle","price":28.5,"currency":"USD","checkout_url":"https://merchant.example/checkout/puzzle-101","commission_plan":{"type":"success_fee","rate_bps":1200,"currency":"USD"}}}'

Fetch a match token by id

Requires explicit consent, verifies the signed MatchToken, proposal id, amount and currency, then returns a merchant handoff with transaction proof and settlement evidence.

curl -X POST https://selltoai.ai/v1/agentic-checkout/chk_xxx/confirm \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer ***' \
  -H 'X-Channel: my-agent' \
  -d '{"match_token_id":"mtk_xxx","proposal_id":"prp_xxx","expected_amount":28.5,"currency":"USD","buyer_confirmation":{"confirmed_by":"gpt-shopper-agent","consent":true,"user_visible_summary":"Buy Montessori Wooden Animal Puzzle for $28.50."}}'

Record an experience decision event

Use after a buyer or user agent picks, rejects, remixes, confirms, or views an experience preview.

curl -X POST https://selltoai.ai/v1/match/mch_xxx/accept \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer MA2A.xxx' \
  -H 'X-Channel: my-agent' \
  -d '{"proposal_id":"prp_xxx"}'

Prepare a proactive experience feed

Returns ready-to-experience proposal shells from taste signals and inspiration references.

curl https://selltoai.ai/v1/match-tokens/mtk_xxx \
  -H 'Authorization: Bearer MA2A.xxx'

Sign an intent mandate

Use only after SellToAI has enabled mandate signing for your integration. Designed for bounded checkout/payment authorization flows.

curl -X POST https://selltoai.ai/v1/decision-events \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer MA2A.xxx' \
  -H 'X-Channel: my-agent' \
  -d '{"event_type":"proposal.remixed","intent_id":"int_xxx","proposal_id":"prp_xxx","action":"change_color","from":"black","to":"cream","reason":"prefers warm minimalist tone","actor_agent_id":"user-agent"}'

Look up a card by recId

Returns ready-to-experience proposal shells from taste signals and inspiration references.

curl -X POST https://selltoai.ai/v1/experience-feed \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer MA2A.xxx' \
  -H 'X-Channel: my-agent' \
  -d '{"agent_id":"user-agent","taste_profile":{"visual_preferences":["warm minimalist","cream palette"],"negative_preferences":["glossy plastic"]},"inspiration_refs":[{"source":"pinterest","url":"https://example.test/pin/1","scene":"small apartment"}],"limit":3}'

Fetch a creator showcase

Use only after Moras has enabled mandate signing for your integration. Designed for bounded checkout/payment authorization flows.

curl -X POST https://selltoai.ai/v1/intent-mandates/sign \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer MA2A.xxx' \
  -d '{"product_id":"3003","amount_limit":129.99}'

Tip — set X-Channel for attribution

Pick any short slug for your agent. Channel-tagged traffic gets a 5× rate-limit if you ask for a key, otherwise 1× still works.

curl https://selltoai.ai/v1/cards/rec_xxxxxxxx \
  -H 'Authorization: Bearer MA2A.xxx'

Fetch a creator showcase

curl 'https://selltoai.ai/v1/creators/eva_creator/showcase?limit=6' \
  -H 'Authorization: Bearer MA2A.xxx'

Tip — set X-Channel for attribution

Pick any short slug for your agent. Channel-tagged traffic gets a 5× rate-limit if you ask for a key, otherwise 1× still works.

X-Channel: <your-agent-slug>