Fred

Fred Get Series

fred_get_series

Read-onlyIdempotent

AUTHORITATIVE historical time-series for US economic indicators from FRED (Federal Reserve Bank of St. Louis — the official US macroeconomic data repository, 800k+ series). Every series is an AGGREGATE for a whole country, state, or METROPOLITAN AREA (e.g. the Phoenix or Oklahoma City metro), reported monthly or quarterly. Pass a series ID like "MORTGAGE30US" (30y mortgage rate), "UNRATE" (unemployment), "CPIAUCSL" (CPI), "GDP", "FEDFUNDS" (Fed funds rate), "HOUST" (housing starts), "RHORUSQ156N" (US homeownership rate — the percent of households that OWN their home, distinct from the mortgage interest rate). Returns dates + values + the indicator's units. Use for macro, Fed, and metro-level indicator questions. If you don't know the series ID, call fred_search first.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Max observations, newest first (1-100000, default 20)
`units`	No	Data transformation: lin (levels), chg (change), ch1 (change from year ago), pch (% change), pc1 (% change from year ago), pca (compounded annual rate of change), cch (continuously compounded rate of change), cca (continuously compounded annual rate of change), log (natural log). Default: lin
`_apiKey`	Yes	FRED API key
`frequency`	No	Frequency aggregation (optional). Codes: d, w, bw, m, q, sa, a — English words also accepted (daily/weekly/biweekly/monthly/quarterly/semiannual/annual).
`series_id`	Yes	FRED series ID (e.g., "MORTGAGE30US", "HOUST", "CSUSHPISA")
`sort_order`	No	Observation order: desc = newest first (default), asc = oldest first.
`observation_end`	No	End date in YYYY-MM-DD format (optional)
`observation_start`	No	Start date in YYYY-MM-DD format (optional)

Output Schema

TableJSON Schema

Name	Required	Description
`note`	No	Present when the list was truncated or an empty request window was widened.
`count`	Yes	Total observations FRED holds for the requested window — NOT the number returned; compare with `returned`.
`units`	No	Units the values are reported in.
`returned`	No	How many observations are actually in `observations` (capped by `limit`, default 20).
`frequency`	No	Publication frequency of the series.
`series_id`	Yes	The requested FRED series ID
`truncated`	No	True when `returned` is less than `count` — raise `limit` to see the rest.
`observations`	Yes	Array of date-value pairs
`series_title`	No	Series title from FRED metadata.
`requested_end`	No	The observation_end the caller passed, echoed back. Absent when the caller passed none.
`observation_end`	No	Last date this series actually covers, from FRED's series metadata.
`requested_start`	No	The observation_start the caller passed, echoed back. Absent when the caller passed none.
`observation_order`	No	Order of the `observations` array. Defaults to newest_first; pass sort_order:'asc' for oldest_first.
`observation_start`	No	First date this series actually covers, from FRED's series metadata.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed14 schema fields changedAug 31, 2026

addedInput schema / properties / sort_order

Added value: +{
+  "description": "Observation order: desc = newest first (default), asc = oldest first.",
+  "enum": [
+    "asc",
+    "desc"
+  ],
+  "type": "string"
+}

changedOutput schema / properties / count / description

Previous value: -"Total number of observations returned"New value: +"Total observations FRED holds for the requested window — NOT the number returned; compare with `returned`."

addedOutput schema / properties / frequency

Added value: +{
+  "description": "Publication frequency of the series.",
+  "type": "string"
+}

addedOutput schema / properties / note

Added value: +{
+  "description": "Present when the list was truncated or an empty request window was widened.",
+  "type": "string"
+}

changedOutput schema / properties / observation_end / description

Previous value: -"End date of observations in YYYY-MM-DD format"New value: +"Last date this series actually covers, from FRED's series metadata."

addedOutput schema / properties / observation_order

Added value: +{
+  "description": "Order of the `observations` array. Defaults to newest_first; pass sort_order:'asc' for oldest_first.",
+  "enum": [
+    "newest_first",
+    "oldest_first"
+  ],
+  "type": "string"
+}

changedOutput schema / properties / observation_start / description

Previous value: -"Start date of observations in YYYY-MM-DD format"New value: +"First date this series actually covers, from FRED's series metadata."

addedOutput schema / properties / requested_end

Added value: +{
+  "description": "The observation_end the caller passed, echoed back. Absent when the caller passed none.",
+  "type": "string"
+}

addedOutput schema / properties / requested_start

Added value: +{
+  "description": "The observation_start the caller passed, echoed back. Absent when the caller passed none.",
+  "type": "string"
+}

addedOutput schema / properties / returned

Added value: +{
+  "description": "How many observations are actually in `observations` (capped by `limit`, default 20).",
+  "type": "number"
+}

addedOutput schema / properties / series_title

Added value: +{
+  "description": "Series title from FRED metadata.",
+  "type": "string"
+}

addedOutput schema / properties / truncated

Added value: +{
+  "description": "True when `returned` is less than `count` — raise `limit` to see the rest.",
+  "type": "boolean"
+}

addedOutput schema / properties / units

Added value: +{
+  "description": "Units the values are reported in.",
+  "type": "string"
+}

changedOutput schema / required

Previous value: -[
-  "series_id",
-  "count",
-  "observation_start",
-  "observation_end",
-  "observations"
-]New value: +[
+  "series_id",
+  "count",
+  "observations"
+]

Changed1 schema field changedAug 6, 2026

addedInput schema / properties / limit

Added value: +{
+  "description": "Max observations, newest first (1-100000, default 20)",
+  "type": "number"
+}

Changed1 schema field changedAug 4, 2026

changedInput schema / examples

Previous value: -[
-  {
-    "_apiKey": "your-fred-api-key",
-    "series_id": "MORTGAGE30US"
-  },
-  {
-    "_apiKey": "your-fred-api-key",
-    "observation_end": "2024-12-31",
-    "observation_start": "2020-01-01",
-    "series_id": "HOUST",
-    "units": "pch"
-  },
-  {
-    "_apiKey": "your-fred-api-key",
-    "series_id": "DBAA"
-  },
-  {
-    "_apiKey": "your-fred-api-key",
-    "observation_start": "2025-01-01",
-    "series_id": "RHORUSQ156N"
-  }
-]New value: +[
+  {
+    "_apiKey": "your-fred-api-key",
+    "series_id": "MORTGAGE30US"
+  },
+  {
+    "_apiKey": "your-fred-api-key",
+    "observation_end": "2024-12-31",
+    "observation_start": "2020-01-01",
+    "series_id": "HOUST",
+    "units": "pch"
+  },
+  {
+    "_apiKey": "your-fred-api-key",
+    "series_id": "DBAA"
+  },
+  {
+    "_apiKey": "your-fred-api-key",
+    "observation_start": "2025-01-01",
+    "series_id": "RHORUSQ156N"
+  },
+  {
+    "_apiKey": "your-fred-api-key",
+    "series_id": "UNRATE"
+  }
+]

Changed1 schema field changedJul 25, 2026

changedInput schema / examples

Previous value: -[
-  {
-    "_apiKey": "your-fred-api-key",
-    "series_id": "MORTGAGE30US"
-  },
-  {
-    "_apiKey": "your-fred-api-key",
-    "observation_end": "2024-12-31",
-    "observation_start": "2020-01-01",
-    "series_id": "HOUST",
-    "units": "pch"
-  },
-  {
-    "_apiKey": "your-fred-api-key",
-    "series_id": "DBAA"
-  },
-  {
-    "_apiKey": "your-fred-api-key",
-    "series_id": "RHORUSQ156N"
-  }
-]New value: +[
+  {
+    "_apiKey": "your-fred-api-key",
+    "series_id": "MORTGAGE30US"
+  },
+  {
+    "_apiKey": "your-fred-api-key",
+    "observation_end": "2024-12-31",
+    "observation_start": "2020-01-01",
+    "series_id": "HOUST",
+    "units": "pch"
+  },
+  {
+    "_apiKey": "your-fred-api-key",
+    "series_id": "DBAA"
+  },
+  {
+    "_apiKey": "your-fred-api-key",
+    "observation_start": "2025-01-01",
+    "series_id": "RHORUSQ156N"
+  }
+]

Changed1 schema field changedJul 24, 2026

changedInput schema / examples

Previous value: -[
-  {
-    "_apiKey": "your-fred-api-key",
-    "series_id": "MORTGAGE30US"
-  },
-  {
-    "_apiKey": "your-fred-api-key",
-    "observation_end": "2024-12-31",
-    "observation_start": "2020-01-01",
-    "series_id": "HOUST",
-    "units": "pch"
-  },
-  {
-    "_apiKey": "your-fred-api-key",
-    "series_id": "DBAA"
-  }
-]New value: +[
+  {
+    "_apiKey": "your-fred-api-key",
+    "series_id": "MORTGAGE30US"
+  },
+  {
+    "_apiKey": "your-fred-api-key",
+    "observation_end": "2024-12-31",
+    "observation_start": "2020-01-01",
+    "series_id": "HOUST",
+    "units": "pch"
+  },
+  {
+    "_apiKey": "your-fred-api-key",
+    "series_id": "DBAA"
+  },
+  {
+    "_apiKey": "your-fred-api-key",
+    "series_id": "RHORUSQ156N"
+  }
+]

Changed1 schema field changedJul 21, 2026

changedInput schema / examples

Previous value: -[
-  {
-    "_apiKey": "your-fred-api-key",
-    "series_id": "MORTGAGE30US"
-  },
-  {
-    "_apiKey": "your-fred-api-key",
-    "observation_end": "2024-12-31",
-    "observation_start": "2020-01-01",
-    "series_id": "HOUST",
-    "units": "pch"
-  }
-]New value: +[
+  {
+    "_apiKey": "your-fred-api-key",
+    "series_id": "MORTGAGE30US"
+  },
+  {
+    "_apiKey": "your-fred-api-key",
+    "observation_end": "2024-12-31",
+    "observation_start": "2020-01-01",
+    "series_id": "HOUST",
+    "units": "pch"
+  },
+  {
+    "_apiKey": "your-fred-api-key",
+    "series_id": "DBAA"
+  }
+]

Changed1 schema field changedJun 27, 2026

changedInput schema / properties / frequency / description

Previous value: -"Frequency aggregation: d, w, bw, m, q, sa, a (optional)"New value: +"Frequency aggregation (optional). Codes: d, w, bw, m, q, sa, a — English words also accepted (daily/weekly/biweekly/monthly/quarterly/semiannual/annual)."

Changed1 schema field changedMay 8, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "count": {
+      "description": "Total number of observations returned",
+      "type": "number"
+    },
+    "observation_end": {
+      "description": "End date of observations in YYYY-MM-DD format",
+      "type": "string"
+    },
+    "observation_start": {
+      "description": "Start date of observations in YYYY-MM-DD format",
+      "type": "string"
+    },
+    "observations": {
+      "description": "Array of date-value pairs",
+      "items": {
+        "properties": {
+          "date": {
+            "description": "Observation date in YYYY-MM-DD format",
+            "type": "string"
+          },
+          "value": {
+            "description": "Numeric value or null if missing",
+            "type": [
+              "string",
+              "null"
+            ]
+          }
+        },
+        "required": [
+          "date",
+          "value"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "series_id": {
+      "description": "The requested FRED series ID",
+      "type": "string"
+    }
+  },
+  "required": [
+    "series_id",
+    "count",
+    "observation_start",
+    "observation_end",
+    "observations"
+  ],
+  "type": "object"
+}

Changed1 schema field changedMay 6, 2026

addedInput schema / examples

Added value: +[
+  {
+    "_apiKey": "your-fred-api-key",
+    "series_id": "MORTGAGE30US"
+  },
+  {
+    "_apiKey": "your-fred-api-key",
+    "observation_end": "2024-12-31",
+    "observation_start": "2020-01-01",
+    "series_id": "HOUST",
+    "units": "pch"
+  }
+]

First observedApr 22, 2026

TDQS

A4.1/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/openWorld/idempotent/non-destructive behavior, so the bar is lower. The description adds meaningful context beyond those hints: series are country/state/metro aggregates, reported monthly or quarterly, and returns include the indicator's units. It does not mention rate limits or update cadence, but nothing here contradicts the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is longer than a minimal one, but the extra sentences are informative: they give concrete series examples, explain the aggregate scope, and state the return shape and search fallback. The key usage instruction ('If you don't know the series ID, call fred_search first') is placed at the end, so the structure is solid if not maximally front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With a rich input schema, output schema, and annotations, the description covers the essential context: what type of data it returns, geographic granularity, example IDs, and the prerequisite search step. It could name more sibling tools for differentiation, but an agent has enough to invoke this tool correctly in most FRED-related queries.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3; the schema already documents series_id, units, frequency, observation dates, limit, and sort order. The description adds real-world meaning for selected series IDs, notably clarifying RHORUSQ156N, but it does not materially explain any parameter that the schema leaves obscure.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies a specific resource (FRED historical economic time-series), requires a series ID, and states the return payload (dates, values, units). It also distinguishes itself from fred_search by telling agents to call fred_search when the series ID is unknown, so it is not confused with sibling data-retrieval tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly says to use this tool for macro, Fed, and metro-level indicator questions, and it names fred_search as the alternative when a series ID is missing. It does not state when to prefer fred_series_info or fred_category, but the main routing decision is covered.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Fred tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.3/5.0

Disambiguation5/5

Every tool has a clearly distinct purpose with detailed descriptions that differentiate even closely related tools like ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded. The FRED and Polymarket tool sets are well-organized with unique responsibilities. No two tools appear to do the same thing.

Naming Consistency4/5

Most tools follow a consistent verb_noun or noun_verb pattern in snake_case (e.g., resolve_entity, compare_entities, list_subscriptions). However, a few tools like 'forget', 'remember', and 'recall' deviate by being single verbs, and 'pipeworx_feedback' uses a noun_verb format. Overall, the naming is predictable but has minor inconsistencies.

Tool Count4/5

With 37 tools covering a broad domain (economic data, prediction markets, company profiles, subscriptions, memory, etc.), the count is reasonable and justifiable. It is slightly above the typical sweet spot but not excessive, and each tool serves a specific purpose. The scope is broad enough to warrant this many tools.

Completeness5/5

The server provides a comprehensive surface for its domain, including CRUD-like operations for data querying (ask_pipeworx, deep_research), specialized tools for prediction markets (arbitrage, edges), and utilities (memory, subscriptions). Obvious operations like entity resolution, comparison, and change tracking are present. No critical gaps are apparent for the stated purpose of querying structured data and engaging with prediction markets.

Fred Get Series

Input Schema

Output Schema

Schema Changelog

TDQS

Glama MCP Gateway

TDQS

Resources