Choose your starting point
The OpenFX MCP connector reads your account data and is read-only. It does not read this documentation and can’t place trades or move funds. Your coding agent writes code that calls the API with your Sandbox API key.
Before you begin
- A Sandbox API key file. The key JSON contains
kidandprivateKey, and Sandbox keys carry asandbox_prefix. See Authentication and Environments. - A coding agent that reads an
AGENTS.mdfile or a project instruction file, such as Claude Code, Codex, Cursor, or GitHub Copilot.
Machine-readable docs
Point your agent at these files so it reads the documentation instead of guessing.
Where a guide page and the OpenAPI specification disagree, the specification is the contract.
Add the rules file and skill
AddAGENTS.md to your repository so every coding agent starts with the OpenFX v3 rules. Add the skill if you use Claude Code. Commit both so every contributor and agent session uses the same rules. They link to the documentation instead of copying it, so they stay current when the documentation changes.
AGENTS.md
AGENTS.md
AGENTS.md is a plain Markdown file at the root of your repository that coding agents read before they work. Copy this file into your repository. It states each rule briefly and links to the page that owns the detail.AGENTS.md
CLAUDE.md, not AGENTS.md. If your repository doesn’t already have a CLAUDE.md, create one that contains the single line @AGENTS.md so Claude Code loads the same rules.SKILL.md (Claude Code)
SKILL.md (Claude Code)
A skill packages a repeatable workflow that Claude Code loads when a request matches its description. Save this file as Codex, Cursor, and GitHub Copilot read
.claude/skills/openfx-integration/SKILL.md in your repository. It sends the agent to the rules file and the matching task prompt, so the rules stay in one place.SKILL.md
AGENTS.md or their own instruction files directly. Skills are specific to Claude Code.Prompt library
Each prompt tells the agent which pages to read, what to build, and what to deliver. The prompts point to the documentation for contract details, so they stay correct when the documentation changes.Use a prompt
1
Copy a prompt
Choose the prompt for your task below and copy its code block.
2
Paste it into your agent
The agent asks for your language, HTTP client, and the path to your Sandbox key file. Answer with paths and names, not secrets.
3
Review and keep the output
Read the code the agent writes, run its tests against Sandbox, and commit the helpers and tests so you can rerun them.
https://docs.openfx.com. If it can’t fetch URLs, paste the pages it names into the conversation.
Start here
Ask a question about the API
Ask a question about the API
Use this in a chat assistant when you don’t have a coding agent open yet.
Sandbox quickstart
Sandbox quickstart
Builds a signing helper, a thin client, and a smoke script that completes one Sandbox trade.
Build a flow
FX quotes and trades
FX quotes and trades
Builds the conversion flow: discover pairs, quote, execute before expiry, and track the trade.
Trade settlement and reversals
Trade settlement and reversals
Builds settle and reverse flows for the settlement model your organization uses.
Payouts end to end
Payouts end to end
Builds recipients, payout addresses, quotes, payouts, confirmation, and lifecycle tracking.
Webhooks end to end
Webhooks end to end
Builds one receiver for every event family with signature verification, deduplication, and state tracking.
Idempotency and retries
Idempotency and retries
Builds persisted idempotency keys, crash recovery, and error-driven retries for every write.
Debug and review
Implement or debug request signing
Implement or debug request signing
Builds a tested JWT and
X-Request-Signature helper, or diagnoses 401 and 403 responses from an existing one.Review an existing integration
Review an existing integration
Audits an integration against the v3 contract and ranks findings by risk to money.
Prepare for Live
Prepare for Live
Verifies readiness and produces a go/no-go report before you switch to Live.
Verify what the agent built
An agent can produce code that looks correct and still fails on the first Live request. Before you rely on it:- Run the integration against Sandbox and confirm it completes a trade or a payout end to end.
- Review the signing helper against Authentication.
- Confirm every write sends an
Idempotency-Keythat is stored before the request. - Confirm webhook handlers verify the signature on the raw body.
- Work through the Live checklist before you switch to a Live key.
What’s next
MCP connectors
Query your account data from an AI app.
Live checklist
Review the full pre-launch checklist.