BePay AI — Agent Documentation

Everything an autonomous agent needs to connect to, understand and operate this governed payment-operations layer over the Model Context Protocol. This is not a mock: every tool below wraps a live function on this server.

Connection

• POST JSON-RPC requests to the endpoint. Single requests and batch arrays are both accepted; responses are plain application/json.
• GET opens a server-sent-events stream carrying periodic pings (for clients that expect the streamable-HTTP GET channel).
• Methods: initialize, notifications/initialized, ping, tools/list, tools/call. Resources and prompts are empty capabilities.
• Sessions are stateless — no Mcp-Session-Id is required or issued.

What this system is

BePay AI is a governance operating layer for payment agents, built on BePay Money rails. The principle: AI proposes. Policy governs. Humans approve. Every task runs a seven-stage governed loop:

• Reasoning — the analysis, planning and reporting inside a run are produced by a live, gateway-managed inference chain. No client keys needed.
• Policy — six deterministic rules (threshold, KYB validity, FX drift, aging, velocity, currency) resolve to BLOCK > HOLD > FLAG > PASS. Worst verdict wins. Policy is code, not model opinion.
• Control plane — each run is admitted as a mission on a real mission-operating platform (create_requirement → approve_mission → store_evidence).
• Approval — payments above 10,000 USD (or under any hold rule) pause the loop for a human decision, recorded on two layers: the payment rail and the mission.
• Proof — every event lands in a SHA-256 hash chain. bepay.get_audit_proof verifies it end-to-end.
• Rails — money movement is a clearly-labeled reference sandbox (deterministic golden dataset). No real funds move. Everything else is live.

Recommended agent loop

1. initialize                       → orient (returns instructions)
2. bepay.overview                   → current system state, health, chain head
3. bepay.list_scenarios             → pick a scenario
4. bepay.start_run {scenario}       → returns run_id (async execution)
5. poll bepay.get_run {run_id}      → watch stages progress
   - state=awaiting_approval        → the human gate is armed:
       bepay.approve_run / bepay.reject_run {run_id, approver}
6. terminal states: completed | blocked | rejected | failed
7. bepay.get_audit_proof            → verify the whole run cryptographically

Tools

Minimal client example

const rpc = async (body) => {
  const r = await fetch('https://sidai.live/beepay/mcp', {
    method: 'POST',
    headers: { 'Content-Type': 'application/json' },
    body: JSON.stringify(body),
  });
  return r.json();
};

await rpc({ jsonrpc:'2.0', id:1, method:'initialize',
  params:{ protocolVersion:'2025-06-18', capabilities:{}, clientInfo:{name:'demo',version:'1'} }});

const tools = await rpc({ jsonrpc:'2.0', id:2, method:'tools/list' });

const started = await rpc({ jsonrpc:'2.0', id:3, method:'tools/call',
  params:{ name:'bepay.start_run', arguments:{ scenario:'hero' } }});
console.log(JSON.parse(started.result.content[0].text).run_id);

Notes & limits

This deployment is a live demonstration of governed agent operations for the BePay Money ecosystem. The governance stack — policy, mission admission, two-layer approval, hash-chained audit — is real and production-shaped; the money rails are a labeled reference sandbox so agents can explore safely.