Loading
Agentic Payments · One run, end to end
Watch an agent run a payout.
Cross-border payouts run on our production rails today — $2.1B settled to date for 50+ fintechs. The trace is what we’re shipping on top: the tool call, the mandate check, the human signature, settled funds.
What your software inherits on day one
$2.1B
Settled to date
0+
Fintechs in production
0
Live corridors
The run
One payout, end to end.
The agent passes every limit and still can’t move money — that’s the design. One signature later, MX$343,539.00 lands — to the centavo.
Agent · MCP
> tools/call payments.quote { from: "USD", to: "MXN", amount: 18450.00 }
< { rate: 18.62 · beneficiary_receives: "MX$343,539.00" · guaranteed: true · window: "SPEI · value today" }
> tools/call runs.request
Mandate · Limits & Approval
agt_7c21… → payroll platform KYB verified → its Head of Treasury
limits ≤ $25,000/txn · ≤ $150,000/day · corridors US→MX, US→BR · expires 2026-12-31
amount ✓ velocity ✓ corridor ✓ recipient ✓
$18,450 > $10,000 approval threshold → human approval required
Approval packet
packet sha256:9f2c…e41a
$18,450.00 → MX$343,539.00 · beneficiary in Mexico · CLABE ••••4907 ✓ check digit · ✓ name match
Signed by the Head of Treasury with a passkey — bound to the exact artifact reviewed.
Settlement
workflow payout.mx.spei · one of 150 versioned workflows
SettledSPEI ref 2026080641772034 · 14:32:07 CST
Beneficiary received MX$343,539.00 — the guaranteed amount, exactly.
Illustrative product UI
That’s the shape a payroll platform’s run will take — yours will run the same way.
What it does for you
The work your software takes over.
Fintech platforms & PSPs
Every failed payment explains itself — and proposes its fix.
A wrong IFSC, a missing purpose code, an IBAN that fails its checksum — the payment comes back with a field-level diagnosis and corrected values, ready to re-run.
Failed-payment reconstruction runs in production inside Mesta today.
payments.track and payments.repair will hand that engine to your software.
Global payroll
Payroll that lands itself in 40+ currencies.
A run is one reviewable object — drafted by your software, every beneficiary validated against the destination country’s rules, executed on schedule.
Every Mesta payment already executes as one of 150 versioned workflows.
workflows.draft and runs.request will let your software drive it.
Marketplaces & MSBs
Onboarding files that check themselves against each country’s rules.
Invoices and onboarding documents validated against per-country requirements — before a human opens the file.
We run this on our own files today, at volume.
beneficiaries.requirements and beneficiaries.validate will expose the same checks.
Treasury
Treasury that runs on the calendar, not on someone’s to-do list.
Scheduled runs move funds across virtual accounts, fiat-to-fiat and stablecoin rails — cut-off-aware, one run object to review.
Scheduled runs and exportable provenance records ship with the tools.
Running today
We automated our own floor first.
These outcomes are not a roadmap deck — they run inside Mesta daily, driven by our own internal agents. What we run internally is what we're packaging for yours.
Documents validate themselves
Our own onboarding queue runs these checks first — every invoice, every file, in production.
Failed payments reconstruct themselves
Diagnosis plus proposed fix — the single hardest job in cross-border, running on our own data.
Compliance review keeps pace
Our AI assembles the evidence; our analysts make the call — at production volume.
In shipping order
What we’re shipping, in order.
First a capability every customer gets. Then the product you buy.
Every payment explains itself
“Where is my money and why did it fail” — ends here. A field-level reason and its repair options, on every payment. It ships first: no new money movement, and the engine behind it already runs our floor.
PaymentFailed
purpose code — required by the destination rail · missing
repair proposed from the rail’s own enum · validated ✓
Apply repair →
The Workflows API
Define a payout process once — recipients, checks, approvals, limits. Run it as one reviewable object, on schedule or on demand, and approve it in one signature. Payroll, supplier runs, marketplace payouts and treasury are this product wearing four names. It works with the plain API calls your backend already makes — agents are one more way to drive it. It ships second.
Workflow · payroll-monthly · v3Awaiting signature
run #08 · 397 payments · every check passed
limits passed · releases on signature
Review & sign →
Illustrative product UI
One MCP server
Every read open. Every write named.
The doors speak MCP. When they open, every ACT call is judged against the mandate your treasurer signed — at the rail, before anything moves; past the threshold, a named human releases it.
Read
Open on connect. Everything Mesta shows, readable.
- Check a corridorcorridors.check
Is this corridor live, on which rails, with what cut-offs.
- Know what a payout needsbeneficiaries.requirements
Every field this country’s payout needs, before you build the form.
- Get a guaranteed quotepayments.quote
A guaranteed landing amount, not an estimate.
- Track the moneypayments.track
Where the money is — and why, in language you can act on.
- Find any operationapi.search
Find the right operation for the job, anywhere in the full API.
- Read anything Mesta showsapi.read
Call any read operation the platform offers. Everything Mesta shows, an agent can read.
Draft
Side-effect-free. A draft can be wrong safely.
Connect
Point your agent at Mesta.
Agent-readable docs
curl https://docs.mesta.xyz/llms.txt
104 operations, indexed for machines. Paste this into any agent today.
MCP — three doors
{
"mcpServers": {
"mesta-docs": { "url": "https://mcp.mesta.xyz/docs" },
"mesta-sandbox": { "url": "https://mcp.mesta.xyz/sandbox",
"auth": { "type": "api_key" } },
"mesta": { "url": "https://mcp.mesta.xyz",
"auth": { "type": "api_key" } }
}
}Three doors, in the order you’ll use them. Docs — no key needed. Sandbox — rehearse the full flow before any money exists. Production — read tools open on connect; every write defers to a person, on keys you already hold. Paste-ready the day they ship; design partners get them first.
One-line install
claude mcp add --transport http mesta https://mcp.mesta.xyz codex mcp add mesta --url https://mcp.mesta.xyz
One line for Claude Code, one for Codex — and anything that speaks MCP connects the same way. Both go live the day the doors open.
The control plane
Controls with names.
Shipping with the tools.
150 versioned workflows
Deterministic execution is how the platform already runs — every payment, every day.
Signed mandate
A signed mandate binds an agent’s key to a KYB-verified entity and a named human — authority you can prove, not a key and a hope.
Hard limits
Amount, velocity, recipient, corridor, expiry — enforced at the rail, not in the prompt.
Approval packets
The packet’s hash is what the passkey signs — swap anything and the signature dies.
Instant revocation
One call ends an agent’s authority — including runs already scheduled.
Provenance records
An exportable record per payment: who asked, what was permitted, who approved, what settled. Built for the person whose job is to ask.
Every approval packet carries a TTL — unsigned by its deadline, it is void, not pending.
The operating business
The hardest frames are the ones we already run.
The easy part of any agent demo is the chat. The hard frames are the CLABE check digit, the name match, the guaranteed landing amount, the settlement window — and those are our operating business today, on real volume, under our licenses and regulated partners.
Banking partners will require a human release above a threshold. We designed for it before being asked — the run you watched is already that shape, and it is the shape SAFR, the industry’s framework for agentic finance at runtime, now describes.
No protocol ships this.
- field-level repair — IBAN · CLABE · IFSC · tax IDs · purpose codes — fixed daily, by people and software that do nothing else
- recalls, run properly
- verification of payee
- guaranteed landing amounts — quoted-versus-sent is a promise, not a surprise
- cut-offs & settlement calendars, known cold
- our licenses and partners, your coverage
The build order
Five phases, none betting on the next.
01Open the doorsThree MCP doors — docs, sandbox, production. Reads open on connect; every write deferred to a named human.
02The engine of trustWorkflows, a ledger reconciliation can’t lie to, mandates enforced by deterministic policy, approvals upgraded to passkey-signed packets, provenance you can export.
03Agents for hireOur measured agents, offered through the same door — your named human still releases the money.
04–05Know Your AgentIdentity for third-party agents. Designed today; built when the world’s agents carry credentials.
What grows, phase over phase, is how much software prepares. The autonomy ceiling never moves.
Every category, one control plane
The map, drawn honestly.
New agent platforms launch at zero — no volume, no licenses, no customers. Ours launches at $2.1B settled to date, 50+ fintechs in production, an AI layer already working our own floor.
Move
Cross-border payments
13 live corridors, 40+ currencies, fiat and stablecoin rails — settled into real local bank accounts under our licenses and regulated partners.
Fiat-to-fiat transfers
Currency to currency, account to account, on the same rails.
On-ramps
From fiat into stablecoin without leaving the platform.
Off-ramps
From stablecoin into local currency, delivered to the beneficiary’s bank account.
Store · Grow · Spend
Store
Virtual accounts
Hold and organize balances on-platform — the store layer your payouts fund from.
Store
Self-custody wallets
Store value in wallets you control, connected to the same rails.
Grow
Stablecoin yields
Put idle balances to work between payouts.
Spend
Stablecoin cards
Spend platform balances directly.
Every category, designed to be operable through the same four objects: mandate, workflow, run, record.
FAQ
Whose agent, whose money, whose signature.
Whose agent runs the payout — yours or ours?
Yours — in the demo, a payroll platform’s mandate, its named human signing the release. The same governance path will serve an agent you run and, later, agents we operate for you: the mandate doesn’t care whose process is calling; it cares who is accountable.
What can my agent do today?
Read our entire API — docs.mesta.xyz serves llms.txt now, and the 104-operation API is live for your backend. The MCP doors — docs, sandbox, production — ship next.
Do agents ever hold funds?
No. On Mesta an agent holds authority, never an account. Your business holds the funds, a mandate you sign will define what software may do with them, and a named human releases anything that moves money. That is the shape regulated cross-border requires — and the one your bank’s risk team will recognize.
How does human approval work?
In the first release, an agent’s write is deferred: it becomes a pending request a person approves in the dashboard before it executes, with webhooks for every state change and an explicit expiry. That gate then upgrades: approvals become packets whose hash a named human signs with a passkey, so what was approved is provably what was reviewed.
Which agents and platforms will be compatible?
Anything that speaks MCP — Claude Code, Codex, Cursor, custom backends — plus plain HTTP for everything else; underneath, it is all the same API. Agent Skills will carry the corridor knowledge — which fields Brazil requires, what a purpose code means, how to recover a rejection — so your agent arrives already knowing the hard parts.
Read the API your agent will read. Start on the 104-operation API today — llms.txt makes all of it agent-readable now.
Open the docs
Agentic payments
Bring your agent.
Point it at the docs today — the tools will land on the API it already reads.