Turn trading signals into controlled execution

TradingView, webhooks, REST API, and AI agents can propose the action

Your Automation binds the source to exact Trading Rules and compatible broker accounts. Vorda checks, routes, and proves every result.

Open my sandboxConnect an AI agent
Routingsources → rules → compatible accounts0/6 compatible
1. A TradingView alert fires, or your AI agent requests a trade through MCP2. Vorda validates it against your risk rules3. Approved workflows execute in sandbox or live routing, with every step logged
How it works

Watch a signal become a checked order

Whether it starts as a webhook or an agent proposal, every step lands in your log. Nothing executes that you can't trace

tradingview → vorda webhook
Vorda order ticketwaiting for webhook
symbol—
side—
size—
strategy—
guardrails—
venue—
order confirmed, proof updated
How the sandbox works

Test one alert before any capital is live

1
Create and test

Create a Signal Source and test it safely. Source tests validate the payload without creating a trade.

2
Bind execution

Create an Automation with one exact Rules version and one to three compatible broker accounts.

3
Start when ready

A running Automation may open new exposure. Stopping it blocks new entries while risk-reducing closes remain available.

Open my sandbox
Venues

Supported execution destinations

Connect one to three compatible broker accounts to an Automation. Every target is evaluated, submitted, reconciled, and proved independently.

Pepperstone cTrader
Pepperstone cTrader
Broker account - demo and live
IC Markets cTrader
IC Markets cTrader
Broker account - demo and live
Alpaca
Alpaca
Broker account - paper and live
Binance Spot
Binance Spot
Exchange account - testnet and live
Binance Futures
Binance Futures
Exchange account - testnet and live
Hyperliquid
Hyperliquid
Exchange account - testnet and live
Don’t see yours?
Request a supported adapter
AI Agent through MCP

AI agents propose. Your Automation decides.

Connect an AI Agent Signal Source through Vorda-hosted MCP. It starts with vorda.propose_action and is designed to expand into scoped positions, execution history, previews, and controlled actions while broker credentials and execution authority stay inside Vorda.

See MCP setup
Agent requestMCP
Current: vorda.propose_action. Planned: scoped account visibility, execution history, previews, and controlled actions through authorized Automations.
Vorda checks the request
Proposal acceptedsource verified
  • Source identity
  • Automation readiness
  • Trading Rules
  • Execution Proof
ChatGPTMCPClaudeMCPClaude CodeMCPCursorMCPVS CodeMCPPyCharmMCPAntigravityMCPHermes AgentMCPOpenClawMCPOdysseusAIMCPCodex or custom MCPMCPDon’t see yours?Request AI agent support
Transparency

It writes down every decision

Execution loglive
09:41:07signal received, source verifiedOK
09:41:07payload normalizedOK
09:41:08Trading Rules passedOK
09:41:08order routed to BinanceSENT
09:41:09fill reconciled, proof completeDONE

Most automation tools fail quietly. You find out when the position is wrong. Vorda works the other way

Traders building with alerts and agents

Built to be trusted with your keys

  • Encrypted credentials
  • Immutable Rules version
  • Compatible Target Set
  • Stop controls
  • Execution Proof
Pricing

Free to test. Paid when you trade live

$0to start

Start in the sandbox

Create sources, rules, and paper Automations without connecting live capital.

Live access is enabled only after broker compatibility, account readiness, and required controls are confirmed.

Open my sandbox

No card to start. Live pricing will be confirmed before activation.

FAQ

Questions traders ask before connecting

Why didn't my TradingView alert execute a trade?

The most common causes are malformed JSON, a wrong symbol, a size cap, a duplicate alert, a closed market, or a broker or exchange rejection. In Vorda, every blocked order carries its reason in the execution log, so you can see which gate stopped it instead of guessing.

Do I need to rewrite my TradingView alerts to use Vorda?

Vorda generates a private source-owned webhook URL and a message template you can customize. Test the payload on the Signal Source before linking it to an Automation.

Can Vorda withdraw money from my exchange account?

No. API keys are scoped to trading only, and Vorda rejects keys with withdrawal permissions during setup. Credentials are stored encrypted and used for order routing, nothing else.

What happens if Vorda goes down when my alert fires?

The webhook fails loudly, not silently. TradingView records the delivery failure, and no order can appear out of nowhere because orders only ever come from a received, validated payload. When service resumes, nothing replays unless your duplicate rules allow it.

What happens when I stop an Automation?

Stopping an Automation blocks new opening exposure for that Automation. Risk-reducing closes can remain available so a stop control does not trap an existing position.

What if my broker or exchange isn't supported yet?

Request it, then test everything else in the sandbox while you wait. Broker and exchange support grows without changing your alert flow, so when yours ships, you connect it and go.

Can ChatGPT or Claude connect to Vorda through MCP?

Yes. Create an AI Agent Signal Source and use its generated MCP connection. The agent can call vorda.propose_action, but it cannot read account context, choose a broker, change Trading Rules, or execute outside a linked running Automation.

What is MCP and do I need it to trade with Vorda?

MCP is the transport used by the AI Agent Signal Source. You only need it when an AI client will propose actions. TradingView and generic webhook sources use their own source-owned connections.

Sandbox

Try one alert or agent check before you connect live capital

Open my sandbox

Free to start. Test Signal Sources before granting execution authority to an Automation.