Fed sentiment

The FOMC sentiment API that scores every Fed statement

Every FOMC statement since 1994 carries one score, from fully dovish to fully hawkish. The tone of the Fed becomes a time series you can chart, screen and backtest.

What you get

What is included?

Everything ships on the same observation model as the rest of the API, with provenance on every row.

244 statements scored

Every FOMC statement since 1994 has a score. New statements are scored automatically after release.

Fixed, versioned lexicon

Scores come from a deterministic lexicon, not a black box model. The lexicon is versioned, so results are reproducible.

Dovish to hawkish in one number

December 2008 reads fully dovish. June 2022 reads fully hawkish. Everything else falls in between.

Three decades of policy tone

The series spans every easing and tightening cycle since 1994, ready for regime analysis.

Point in time

Each score is tied to the statement's release moment, so backtests line up with what markets knew.

JSON, SDK and MCP

Pull it over REST, the typed TypeScript client or the hosted MCP server for agents.

Methodology

How is Fed sentiment scored?

Each statement is scored with a fixed lexicon of hawkish and dovish language built for central bank communication. Because the lexicon is versioned and deterministic, the same statement always produces the same score, and you can trace any reading back to the exact statement text behind it.

That makes the series safe for research. A model score that silently changes over time cannot be backtested honestly. A versioned lexicon can.

GET/v1/observations?indicator=cb_statement_sentiment&country=usa&period_start=2022-06-01&period_end=2022-06-30200 OK
{
  "data": [{
    "entityId": "country_usa",
    "indicatorId": "indicator_cb_statement_sentiment",
    "valueNumeric": 1,
    "periodEnd": "2022-06-15T00:00:00.000Z",
    "revisionStatus": "final",
    "rights": {
      "exposureClass": "public_api_allowed",
      "redistributionAllowed": "allowed"
    }
  }],
  "meta": { "api_version": "v1", "pagination": { "limit": 1, "has_more": false } }
}

A real row from the live API: the June 15, 2022 statement, the meeting of the 75 basis point hike. A score of 1 is fully hawkish, minus 1 is fully dovish.

Use cases

What can you build with an FOMC sentiment API?

Rates and FX strategies use the score as a policy regime filter. Dashboards chart the tone of the Fed alongside inflation and the policy rate. Researchers study how markets react when tone shifts faster than the dot plot.

Agents can ask for it in plain language. The hosted MCP server exposes the sentiment series as a tool, so Claude, Cursor or any MCP client can pull the latest reading or the full history with no glue code.

Questions

Common questions

The short answers, straight from the documentation.

Get started

Start with the macro data, ship the rest faster

Free tier, no card. One key, one API and every macro number, with a hosted MCP server for your agent.

Get your free API key
Night sky over a mountain horizon