# Fred (npm · @pipeworx/mcp-fred)

FRED MCP — Federal Reserve Economic Data (St. Louis Fed)

- Trust score: 82/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `gateway.pipeworx.io`: 63/100, [markdown](https://verifymcp.io/servers/pipeworx-io-fred/fred-mcp.md), [page](https://verifymcp.io/servers/pipeworx-io-fred/fred-mcp)
- npm · `@pipeworx/mcp-fred`: 82/100 (this document), [markdown](https://verifymcp.io/servers/pipeworx-io-fred/pipeworx-mcp-fred.md), [page](https://verifymcp.io/servers/pipeworx-io-fred/pipeworx-mcp-fred)

## Channel facts

- Registry: `npm`
- Package: `@pipeworx/mcp-fred`
- Version: `0.2.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to pipeworx-io/mcp-fred).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 3 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 64/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2120 tokens (~212/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Fred MCP server?

Fred runs locally as an npm package, launched with npx -y @pipeworx/mcp-fred. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add pipeworx-io-fred -- npx -y @pipeworx/mcp-fred
```

### Cursor

```json
{
  "mcpServers": {
    "pipeworx-io-fred": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/mcp-fred"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "pipeworx-io-fred": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/mcp-fred"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add pipeworx-io-fred -- npx -y @pipeworx/mcp-fred
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "pipeworx-io-fred": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@pipeworx/mcp-fred"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add pipeworx-io-fred --command npx --arg -y --arg @pipeworx/mcp-fred
```

### Hermes

```yaml
mcp_servers:
  pipeworx-io-fred:
    command: "npx"
    args: ["-y", "@pipeworx/mcp-fred"]
```

### Netclaw

```json
{
  "McpServers": {
    "pipeworx-io-fred": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@pipeworx/mcp-fred"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add pipeworx-io-fred -t stdio -c npx -a -y @pipeworx/mcp-fred
```

### Other

```json
{
  "mcpServers": {
    "pipeworx-io-fred": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/mcp-fred"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 81, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-02 (score 66, −13)

- [security regression] Malware scan: pass → unverified
- [functional improvement] Stability: unverified → 0.13
- [functional] Package version: 0.2.0 → 0.2.1

### 2026-10-31 (score 79, 0)

- [functional regression] Security disclosure: unverified → fail

### 2026-10-29 (score 79)

First indexed and scored.

## MCP tools (10)

### `fred_get_series` (~734 tokens)

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 US indicator questions. DO NOT GUESS a non-US series ID by pattern-matching a US one — "DEUUNRATE", "JPNUNRATE", "CANUNRATE" and similar <ISO3><METRIC> codes do NOT exist on FRED and 400 with "the series does not exist". For a NON-US country's unemployment/GDP/inflation/population, use worldbank_get_indicator (ISO country code + indicator, e.g. SL.UEM.TOTL.ZS for unemployment) instead — it is the reliable source for foreign macro data. If you don't know a FRED series ID, call fred_search first rather than inventing one.

Input parameters:

- `_apiKey` (string, required): FRED API key
- `as_of` (string): ALFRED vintage query: return the data as it was PUBLISHED on this date (YYYY-MM-DD), before any later revisions. Shorthand for realtime_start=realtime_end=as_of. Omit for the default: today's latest-…
- `frequency` (string): Frequency aggregation (optional). Codes: d, w, bw, m, q, sa, a — English words also accepted (daily/weekly/biweekly/monthly/quarterly/semiannual/annual).
- `limit` (number): Max observations, newest first (1-100000, default 20)
- `observation_end` (string): End date in YYYY-MM-DD format (optional)
- `observation_start` (string): Start date in YYYY-MM-DD format (optional)
- `realtime_end` (string): ALFRED vintage query: end of the realtime (publication) window, YYYY-MM-DD. See realtime_start.
- `realtime_start` (string): ALFRED vintage query: start of the realtime (publication) window, YYYY-MM-DD. Use with realtime_end for a custom vintage range; use `as_of` for the common single-date case. Omit for the default lates…
- `series_id` (string, required): FRED series ID (e.g., "MORTGAGE30US", "HOUST", "CSUSHPISA")
- `sort_order` (string): Observation order: desc = newest first (default), asc = oldest first.
- `units` (string): 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…

### `fred_vintage_dates` (~168 tokens)

ALFRED revision history: every date FRED published a new vintage (initial release or a later revision) of a series. Use before fred_revisions to see which dates have a distinct vintage, or pass one of these dates as `as_of`/`realtime_start`+`realtime_end` to fred_get_series to get the data as it stood on that date.

Input parameters:

- `_apiKey` (string, required): FRED API key
- `limit` (number): Max vintage dates to return (1-10000, default 100)
- `series_id` (string, required): FRED series ID (e.g., "GDPC1", "PAYEMS")
- `sort_order` (string): asc = oldest vintage first, desc = newest vintage first (default desc)

### `fred_revisions` (~204 tokens)

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.

Input parameters:

- `_apiKey` (string, required): FRED API key
- `observation_date` (string, required): 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).
- `series_id` (string, required): FRED series ID (e.g., "GDPC1", "PAYEMS")

### `fred_search` (~161 tokens)

Search for economic data series by keyword. Returns series IDs, titles, and descriptions to identify the right indicator.

Input parameters:

- `_apiKey` (string, required): FRED API key
- `limit` (number): Max results to return (1-1000, default 20)
- `order_by` (string): Order results by: search_rank, series_id, title, units, frequency, seasonal_adjustment, realtime_start, realtime_end, last_updated, observation_start, observation_end, popularity, group_popularity. D…
- `search_text` (string, required): Keywords to search for (e.g., "mortgage rate", "housing starts")
- `sort_order` (string): Sort direction: asc or desc. Default: asc for search_rank

### `fred_series_info` (~73 tokens)

Get metadata for a series: title, units, frequency, seasonal adjustment, notes, and date range. Check this before fetching historical data.

Input parameters:

- `_apiKey` (string, required): FRED API key
- `series_id` (string, required): FRED series ID (e.g., "MORTGAGE30US")

### `fred_category` (~66 tokens)

Browse economic data by category (housing, employment, money/banking, etc.). Returns subcategories and related series IDs.

Input parameters:

- `_apiKey` (string, required): FRED API key
- `category_id` (number): Category ID to browse children of (default: 0 for root)

### `fred_releases` (~75 tokens)

Check upcoming and recent economic data releases. Returns release dates, names, and which series they update.

Input parameters:

- `_apiKey` (string, required): FRED API key
- `limit` (number): Max results (1-1000, default 20)
- `offset` (number): Result offset for pagination (default 0)

### `fred_release_dates` (~197 tokens)

Economic data RELEASE CALENDAR from FRED — the dates indicators are/were published, including FUTURE scheduled dates. PREFER OVER WEB SEARCH for "when is the next CPI / jobs report / GDP release", "economic calendar", "Fed data release schedule". Omit release_id for the cross-release calendar; pass a release_id (from fred_releases — e.g. 10 = CPI, 50 = Employment Situation, 53 = GDP) for one release schedule. Returns release name + date, newest/upcoming first by default.

Input parameters:

- `_apiKey` (string, required): FRED API key
- `limit` (number): Max dates to return (1-1000, default 25)
- `release_id` (number): Optional FRED release id (from fred_releases). Omit for the all-releases calendar.
- `sort_order` (string): asc or desc (default desc — newest/upcoming first)

### `nyfed_gdp_nowcast` (~240 tokens)

The New York Fed Staff Nowcast — a weekly real GDP growth nowcast for the currently-tracked US quarter(s), from the Federal Reserve Bank of New York (keyless, NOT a FRED series — FRED's own catalog does not carry this). Answers "what is the NY Fed GDP nowcast", "current GDP growth estimate", "is the economy growing this quarter". Returns the headline nowcast percentage (annualized QoQ) for the quarter(s) actively being tracked (typically the most recent quarter awaiting its official BEA GDP release, plus the quarter in progress), with 50%/80% probability intervals where published, the publisher's own narrative explaining what moved the estimate this week, and recent CONCLUDED quarters' final nowcast versus the actual BEA advance/latest GDP print. Updated every Friday (except federal holidays).

Input parameters:

- `history_quarters` (number): How many concluded quarters of history to include (default 6, max 20). Ignored if include_history is false.
- `include_history` (boolean): Include recent CONCLUDED quarters (final nowcast vs. actual BEA GDP). Default true.

### `cleveland_fed_inflation_nowcast` (~151 tokens)

Daily CPI and PCE inflation nowcasts (headline and core) from the Federal Reserve Bank of Cleveland — keyless, NOT a FRED series. Answers "what is the Cleveland Fed inflation nowcast", "current CPI estimate before the official release", "PCE inflation nowcast today". Returns month-over-month and year-over-year nowcasts for the current and prior month, plus quarterly annualized nowcasts for the current and next quarter. A blank value for a period/measure means the actual BLS (CPI) or BEA (PCE) release for that period has already been published, so the nowcast model stops estimating it. Updated every business day.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/pipeworx-io-fred/pipeworx-mcp-fred#diagnostics

## Score history

- 2026-11-05: 82
- 2026-11-04: 82
- 2026-11-03: 81
- 2026-11-02: 66
- 2026-11-01: 79
- 2026-10-31: 79
- 2026-10-30: 79
- 2026-10-29: 79

## Common questions

### What is the Fred MCP server?

Fred is an MCP server listed in the public MCP registry as io.github.pipeworx-io/fred. FRED MCP, Federal Reserve Economic Data (St. Louis Fed). This page covers its npm package (@pipeworx/mcp-fred).

### Is the Fred MCP server safe to use?

Fred scores 82 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Fred MCP server expose?

Fred exposes 10 tools: fred_get_series, fred_vintage_dates, fred_revisions, fred_search, fred_series_info, and 5 more. Their descriptions and schemas cost roughly 2,069 tokens of context every time the server is loaded.

### Is the Fred MCP server still maintained?

Fred is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Fred MCP server under?

Fred declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the Fred MCP server?

VerifyMCP ran 16 checks on Fred, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- npm package: https://www.npmjs.com/package/@pipeworx/mcp-fred
- Socket report: https://socket.dev/npm/package/@pipeworx/mcp-fred
- Repository: https://github.com/pipeworx-io/mcp-fred
- Website: https://pipeworx.io/packs/fred
- Changelog RSS feed: https://verifymcp.io/servers/pipeworx-io-fred/pipeworx-mcp-fred.xml
- Changelog JSON feed: https://verifymcp.io/servers/pipeworx-io-fred/pipeworx-mcp-fred/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/pipeworx-io-fred/pipeworx-mcp-fred.json
- HTML version of this page: https://verifymcp.io/servers/pipeworx-io-fred/pipeworx-mcp-fred