YG3 MCP — agent integration

Connect autonomous agents to YG3 marketing operations: content and SEO, outbound email, LinkedIn, and paid ads.

No signup required for agent builds. One HTTP call provisions a sandbox workspace and returns a Bearer token for MCP.

Quick start (agent path)

# 1. Provision — no auth
curl -s -X POST https://agency.yg3.ai/api/v1/workspaces \
  -H "Content-Type: application/json" \
  -d '{"domain":"acme.com","industry":"Plumbing","location":"Tampa, FL"}'

# Response includes: token, mcp_endpoint, workspace.url, claim_endpoint

# 2. List MCP tools
curl -s -X POST https://mcp.yg3.ai/mcp \
  -H "Authorization: Bearer YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

# 3. Call a tool
curl -s -X POST https://mcp.yg3.ai/mcp \
  -H "Authorization: Bearer YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"get_client_snapshot","arguments":{}}}'

Python example: examples/provision-and-call.py

Related MCP server: Google Ads MCP Server

Tools

197+ MCP tools (live count: https://mcp.yg3.ai/api/health). Common entry points:

Full catalog after connecting: tools/list or GET https://mcp.yg3.ai/api/health.

Human path (OAuth)

If the human already has a YG3 account:

1. Add https://mcp.yg3.ai/mcp as a custom MCP connector

2. Sign in when prompted

3. Setup guide: https://www.yg3.ai/connect

Claude Code:

claude mcp add --transport http yg3 https://mcp.yg3.ai/mcp

Cursor / VS Code MCP config: see examples/cursor-mcp.json

Agent path (no login)

Provision

POST https://agency.yg3.ai/api/v1/workspaces
Content-Type: application/json

{
  "domain": "acme-plumbing.com",
  "industry": "Plumbing",
  "location": "Tampa, FL"
}

Optional: "name" if you have no domain yet.

201 response:

Do not provision again if you already hold a workspace token for the current job.

MCP

All calls are JSON-RPC 2.0 over HTTP:

POST https://mcp.yg3.ai/mcp
Authorization: Bearer <token>

Methods: tools/list, tools/call, resources/read, initialize

Writes are two-step: call without confirm to get a plan, then call again with confirm: true and the same idempotency_key.

Claim (human takes over)

POST https://agency.yg3.ai/api/v1/workspaces/claim
Authorization: Bearer <workspace-token>

{"email": "owner@example.com", "password": "..."}

If the email already has a YG3 account, omit password — the workspace attaches to that account.

Delete a test workspace

DELETE https://agency.yg3.ai/api/v1/workspaces
Authorization: Bearer <workspace-token>

Only unclaimed workspaces. Archived, not erased.

Discovery

After connecting, read platform docs via MCP:

• yg3://docs/agent-integration

• yg3://docs/getting-started

• yg3://docs/tools-reference

Sandbox limits

Unclaimed workspaces are free-tier sandboxes by design:

• Can: read everything, set profile/brand/voice, design site, write and publish articles to blog-{slug}.yg3.ai

• Cannot: custom domain, email sends, ad spend, LinkedIn posts

• Expires: 14 days unless claimed

For agent frameworks

Copy AGENTS.md into your repo or point your agent at this README. It tells coding agents when and how to provision YG3 during a build.

ClawHub (OpenClaw)

Publishable skill: skills/yg3-marketing-mcp/SKILL.md

clawhub login
clawhub skill publish ./skills/yg3-marketing-mcp --slug yg3-marketing-mcp --name "YG3 Marketing MCP"

Moltbook / curl-based agents

Curlable skill files (Moltbook-style): distribute/

• Install doc: distribute/skill.md

• Periodic routine: distribute/heartbeat.md

• Metadata: distribute/skill.json

Agents can fetch from raw GitHub once this repo is public, or from https://www.yg3.ai/llms.txt.

Registry listings

Registry namespace: io.github.YG3-ai/yg3-mcp

Related

• Elysia LLM API (text/vision/image models): https://www.yg3.ai/for-developers

• Quill (multi-AI thinking partner, PyPI): https://github.com/YG3-ai/quill

License

MIT — see LICENSE.