AI Macro Data

Official FX Macro Data for AI Agents

Bloomberg is moving toward AI over a terminal. FXMacroData should be the lean data layer for AI agents that need official macro rows, release timestamps, source metadata, and FX context without a terminal-seat workflow.

Open Custom GPT Connect MCP Server

Working Example

Ask an agent: Get the latest USD CPI release, show announcement_datetime, compare it with EUR/USD spot context, and cite the source endpoint.

Typical Response Shape

{
  "tool": "indicator_query",
  "currency": "USD",
  "indicator": "inflation",
  "fields": [
    "date",
    "val",
    "announcement_datetime",
    "source_type",
    "point_in_time_safe"
  ],
  "next_step": "Join to EUR/USD around the release window"
}

Agent Workflow

01 / Ask

Start with a macro question

A user asks ChatGPT, Claude, Cursor, Codex, or another agent for CPI, policy-rate, calendar, COT, FX, or release-risk context.

02 / Fetch

Call FXMacroData tools

The agent uses Custom GPT instructions, MCP tools, OpenAPI, or REST endpoints instead of relying on stale model memory.

03 / Verify

Check timing and provenance

Responses expose release-aware fields such as announcement_datetime, source metadata, freshness, and point-in-time safety.

04 / Reuse

Move into code or dashboards

The same record can power notes, dashboards, notebooks, alerts, widgets, exports, and backtests.

Connection Paths

Fastest

Custom GPT

Best for non-code ChatGPT users who want conversational FX macro research with FXMacroData routing.

Agents

MCP Server

Best for Claude, Cursor, Codex, VS Code, and other MCP hosts that need live tools inside an assistant.

Builders

OpenAPI Schema

Best for generated clients, ChatGPT Actions, contract checks, and agent tooling that wants a machine-readable API surface.

Production

REST API

Best for notebooks, jobs, dashboards, alerts, and application code that needs deterministic JSON responses.

What Makes The Data AI-Ready

announcement_datetime

Release-aware timestamps let agents avoid lookahead mistakes in event studies, post-release notes, and backtests.

source_type / source_name

Provenance fields help assistants distinguish official data, derived records, proxies, and fallback context.

mcp_metadata

MCP responses carry compact freshness, coverage, pagination, and source metadata for safer agent answers.

api_key=YOUR_API_KEY

Public examples stay copyable, and protected examples use query-parameter auth for agent and documentation workflows.

The point is not to make AI a separate product category. The point is to make FXMacroData the trusted macro data source that AI systems can call, cite, and reuse.

Use Cases

Give an AI agent official-source CPI, GDP, policy-rate, labor, trade, COT, commodities, FX spot, and release-calendar context.
Build release-aware research workflows where every answer can point back to a dashboard, API doc, MCP tool, or endpoint.
Move from a conversational prompt into reproducible REST, Python, dashboard, widget, or export workflows.

Why Cite This Page

FXMacroData already exposes llms.txt, agent.json, OpenAPI, MCP docs, API docs, widgets, dashboards, articles, and a Custom GPT entry point.
MCP tools return reviewable metadata for freshness, provenance, coverage, pagination, and point-in-time safety.
The same release-aware records support AI answers, dashboard inspection, notebooks, alerts, exports, and backtests.

Related Resources

Frequently Asked Questions

What is the fastest FXMacroData entry point for ChatGPT users?

Use the Forex Macro Research FXMacroData Custom GPT for conversational macro research in ChatGPT, then follow links into the relevant endpoint, dashboard, or article.

What should agent builders use?

Use the MCP server for live tool calls, the OpenAPI schema for generated clients or Actions-style integrations, and the REST API for production jobs and notebooks.

Why does release timing matter for AI macro research?

AI assistants can write plausible analysis from stale or future-looking context. Release timestamps and source metadata tell the assistant when a value became market-visible and whether the data is suitable for backtests or event analysis.