`fred_revisions`

Pack: fred · Connect: https://pipeworx.io/mcp (see Connect below for a single-pack URL)

No MCP client? Call it directly: GET https://gateway.pipeworx.io/v1/tools/fred_revisions for the schema, then POST the same URL with its arguments for the data.

The revision history of one observation in a FRED series, across every ALFRED vintage.

Tool description as the model sees it

How ONE observation (one date) in a FRED series was revised over time, from first release through every later vintage to the latest. Use on series that get revised after initial publication (e.g. GDP “GDPC1”, payrolls “PAYEMS”) to see the originally reported value versus the current one. Returns every ALFRED vintage on record for that observation, oldest first — consecutive vintages can repeat the same value, so compare first_release.value to latest.value (or scan revisions) to see whether it was ever actually revised.

Parameters

Name	Type	Required	Description
`series_id`	string	yes	FRED series ID (e.g., “GDPC1”, “PAYEMS”)
`observation_date`	string	yes	The observation date to trace revisions for, YYYY-MM-DD (must match an actual observation date in the series — e.g. the first day of the quarter for quarterly series).
`_apiKey`	string	yes	FRED API key

Example call

Arguments

{
  "series_id": "GDPC1",
  "observation_date": "2023-10-01"
}

curl

curl -X POST https://gateway.pipeworx.io/fred/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"fred_revisions","arguments":{"series_id":"GDPC1","observation_date":"2023-10-01"}}}'

TypeScript (@pipeworx/sdk)

import { Pipeworx } from '@pipeworx/sdk';
const pipeworx = new Pipeworx();

const result = await pipeworx.call('fred_revisions', {
  "series_id": "GDPC1",
  "observation_date": "2023-10-01"
});

More examples

{
  "series_id": "PAYEMS",
  "observation_date": "2025-08-01"
}

Response shape

Always returns: series_id, observation_date, revisions_count, first_release, latest, revisions

Field	Type	Description
`series_id`	string	The requested FRED series ID
`observation_date`	string	The observation date whose revision history this is
`revisions_count`	number	How many ALFRED vintages are on record for this observation — NOT how many times the value changed (consecutive vintages can repeat the same value; compare first_release.value to latest.value).
`note`	string	Present only when no observation was found for the given date.
`first_release`	object \| null	The earliest-recorded vintage for this observation, or null if none found.
`latest`	object \| null	The most recently recorded vintage for this observation, or null if none found.
`revisions`	array	Every ALFRED vintage on record for this observation, oldest first.

Full JSON Schema

{
  "type": "object",
  "properties": {
    "series_id": {
      "type": "string",
      "description": "The requested FRED series ID"
    },
    "observation_date": {
      "type": "string",
      "description": "The observation date whose revision history this is"
    },
    "revisions_count": {
      "type": "number",
      "description": "How many ALFRED vintages are on record for this observation — NOT how many times the value changed (consecutive vintages can repeat the same value; compare first_release.value to latest.value)."
    },
    "note": {
      "type": "string",
      "description": "Present only when no observation was found for the given date."
    },
    "first_release": {
      "type": [
        "object",
        "null"
      ],
      "description": "The earliest-recorded vintage for this observation, or null if none found.",
      "properties": {
        "vintage_date": {
          "type": "string",
          "description": "The ALFRED vintage date (YYYY-MM-DD) this value was recorded under."
        },
        "value": {
          "type": [
            "string",
            "null"
          ]
        }
      }
    },
    "latest": {
      "type": [
        "object",
        "null"
      ],
      "description": "The most recently recorded vintage for this observation, or null if none found.",
      "properties": {
        "vintage_date": {
          "type": "string"
        },
        "value": {
          "type": [
            "string",
            "null"
          ]
        }
      }
    },
    "revisions": {
      "type": "array",
      "description": "Every ALFRED vintage on record for this observation, oldest first.",
      "items": {
        "type": "object",
        "properties": {
          "vintage_date": {
            "type": "string"
          },
          "value": {
            "type": [
              "string",
              "null"
            ]
          }
        }
      }
    }
  },
  "required": [
    "series_id",
    "observation_date",
    "revisions_count",
    "first_release",
    "latest",
    "revisions"
  ]
}

Connect

Add this to your MCP client config — every tool in the catalog, including this one — or use one-click install buttons:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://pipeworx.io/mcp"
    }
  }
}

Connect to just the fred pack

{
  "mcpServers": {
    "fred": {
      "url": "https://gateway.pipeworx.io/fred/mcp"
    }
  }
}

See Getting Started for client-specific install steps.

fred_revisions