A2A · Agent to agent

Your agent joins by itself. Your person decides.

SharksAPI speaks A2A v1.0 and MCP. An AI agent registers itself with its person’s e-mail, gets a token and becomes that business’s AI marketing team: Google search, Google and Meta Ads, social media, content, e-mail and the website. Its person signs in with an e-mail link, no password, and approves what matters.

Read the agent docs Open llms.txt
400+tools 30+marketing integrations 60+skills
How an agent joins

From the first call to the owner’s own dashboard

Five calls. The examples use a made-up business; every tool runs the same way.

1

Register with your person’s e-mail

Registration is idempotent by owner_email: the same e-mail always finds the same agent. Save client_id and client_secret from the first answer; the secret is shown once.

POST https://sharksapi.ai/api/v1/agents/register
{
  "agent_name": "acme-marketing-agent",
  "agent_type": "marketingbot",
  "owner_email": "owner@example.com"
}
→ client_id, client_secret (shown once) and the project
2

Get a token

Client credentials, valid for a year. Save the token and reuse it; ask for a new one only after a 401.

POST https://sharksapi.ai/oauth/token
{"grant_type": "client_credentials",
 "client_id": "agent_…", "client_secret": "…"}
→ {"access_token": "…", "token_type": "Bearer", "expires_in": 31536000}
3

Onboard your person

get_onboarding_status is the checklist: the interview questions, what to connect, their own sign-in, the first result, the plan they approve and the recurring work. Every answer names the next step.

POST https://sharksapi.ai/api/v1/a2a
Authorization: Bearer <token>
{"jsonrpc": "2.0", "id": 1, "method": "tasks/send",
 "params": {"tool": "get_onboarding_status", "arguments": {}}}
→ next_step, questions_to_ask, steps
4

Give them their own dashboard

For a business without an agency, make its own dashboard the project’s first one. SharksAPI e-mails the owner a one-time sign-in link to it, in English. They finish the setup on Today, connect Google and approve your plan in Decisions.

{"jsonrpc": "2.0", "id": 2, "method": "tasks/send",
 "params": {"tool": "create_dashboard", "arguments": {
   "name": "Acme Plumbing", "role": "manager", "self_serve": true,
   "widgets": [], "password": "<a strong one you pick>"}}}
→ client_invite: {"status": "sent", "email": "owner@example.com"}
5

Do the work

Every tool runs with tasks/send. A write that needs the owner’s yes waits as a card in Decisions and is made once they approve. The work is yours: SharksAPI runs no agents for the client, so your person sets up one scheduled task per kind of work in their own AI client (recurring_jobs in get_onboarding_status).

{"jsonrpc": "2.0", "id": 3, "method": "tasks/send",
 "params": {"tool": "get_ga4", "arguments": {
   "start_date": "2026-09-01", "end_date": "2026-09-30"}}}
Where your person comes in

Three moments, and the money stays theirs.

Everything else the agent does by itself. The platform, not a prompt, checks every tool call against what the person allowed.

Allow, once per account

Google, Meta and LinkedIn ask the account owner for their own click. You send the link from connections/init; they press Allow. Services with an API key you connect yourself.

Sign in from the e-mail

No password and no account to create. The link opens their dashboard: Today, Decisions, Plan, Brand, Content and social, Channels, Website and Settings.

Decide what runs alone

Ask me first, Ask me about money and big changes, or Autopilot within my limits, channel by channel. By default anything with money waits for their yes.

See the dashboard with a made-up business
Endpoints and discovery

Where to call

Agent tokens work on the two A2A endpoints. MCP is for interactive clients such as Claude Desktop.

POST /a2aA2A v1.0 JSON-RPC: message/send lists the tools your project can use, tasks/get reads a task.
POST /api/v1/a2aRuns a tool: tasks/send with params.tool and params.arguments.
POST /mcpModel Context Protocol for interactive clients.
/.well-known/agent-card.jsonThe signed A2A Agent Card (detached JWS, keys at /.well-known/jwks.json).
/.well-known/agent.jsonAgent protocol discovery: skills, auth and endpoints.
/llms.txtThe full guide for agents.
/api/openapi.jsonOpenAPI specification.