FRED API

# Fix list: FRED API

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/fred, the October 2026 research run, assessed 9 October 2026. Grade E, 42.7 out of 100.

This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.

For a coding agent working on FRED API: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.

## 1. Reliability, 38 out of 100, up to 12.4 more on the total

Why it scored 38: Graded as a hosted API. No status page was found in the API docs, the FRED footer or the help pages (0), so there is no incident history to read (5). Rate limits are published, 120 requests a minute on version 1 and two a second on version 2 (15). The errors pages document 429 and warn of a temporary block, with no Retry-After header or backoff guidance. Every request is a read (8 of 15). No SLA, and the terms disclaim availability (0). Both versions are published without a beta label (10). 0 + 5 + 15 + 8 + 0 + 10 = 38.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 10, the surface agents use is generally available, not beta or preview.

Local packages, SDKs, frameworks and stdio MCP servers.

- 20, installs from an official package with supported runtimes stated.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 15, version 1.0 or later, or declared stable.

Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.

## 2. Security & auth, 35 out of 100, up to 11.4 more on the total

Why it scored 35: One 32-character key for each application, with no scopes. Version 1 documents the `api_key` query parameter as its only method, so the secret travels in the URL, and version 2 moves it to a bearer header. Key deletion or rotation sits behind the account login and was not seen (20 less 10, 10 of 30). The API is read-only (15 of 20). Responses are curated statistics with series notes written by FRED or its sources (10 of 15). No request log or usage view was found (0 of 15). security.txt returns 404 on fred.stlouisfed.org and api.stlouisfed.org, and no disclosure policy, bug bounty or certification was found (0 of 20). Total 35.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.
- 0 to 15, audit logs or per-call visibility for the operator.
- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.

Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.

## 3. Schema & documentation, 43 out of 100, up to 9.3 more on the total

Why it scored 43: No OpenAPI or other machine-readable contract was found in the docs (0). fred.stlouisfed.org/llms.txt returns 404 (0). Each of the 31 version 1 requests has a description and a parameter list, and real-time periods have their own page, with little on when to choose one request over another (12 of 20). Parameters state type, range, default and allowed values in prose, such as nine `units` values and `limit` between 1 and 100,000 (12 of 15). Each page shows example requests and responses in XML and JSON, and the errors pages list status codes with sample bodies (12 of 15). Version 2 has its own path and a dated launch note, version 1 has no version in its path, and there is no API changelog (7 of 15). Total 43.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 15, versioning and a public changelog.

Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.

## 4. Payments & pricing, 40 out of 100, up to 7.5 more on the total

Why it scored 40: No x402, MPP or L402 (0). Free, stated publicly, with nothing to buy (20). No card (20). A person has to create a FRED account and request the key in a browser (0). Total 40.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).

- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.
- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login.
- 20, a free tier or trial that doesn't need a card.
- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).

Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.

Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.

## 5. Maintenance & community, 15 out of 100, up to 7.4 more on the total

Why it scored 15: The last dated API change found is the version 2 launch on 4 November 2025, 339 days before the check (0 of 30). The FRED News feed carries eight posts in the last 90 days, four of them data additions and none an API change, so half credit (10 of 20). A public news feed and a contact form, with no developer forum or issue tracker found (5 of 15). No official SDK (0 of 15). No package to judge (0 of 10). The official MCP connector is recent but its launch date was not found, so it earns nothing here. Total 15.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## 6. Agent ergonomics, 68 out of 100, up to 5.2 more on the total

Why it scored 68: `limit`, `observation_start`, `observation_end`, frequency aggregation and `units` size an observations response, with no field selection and defaults of 100,000 and 500,000 observations (15 of 25). `limit` and `offset`, cursor paging on version 2, `order_by`, `filter_variable` and tag filters (18 of 20). Errors carry a status code and a message naming the failing variable, in a short list of codes (13 of 20). All requests are GETs and safe to retry (15 of 20). An observations call needs only `series_id` and the key, but version 1 answers in XML unless `file_type=json` is set, and no official SDK was found (7 of 15). Total 68.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.

Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.

## 7. Transparency & trust, 53 out of 100, up to 4.1 more on the total

Made of editorial 37, provenance 69.

Why it scored 53: Closed service with published terms. Two documents carry API terms and differ. The page the API docs link lacks the clauses on AI training, caching and wholesale downloading that the FRED Services Terms of Use add, and neither is dated (12 of 30). The Online Privacy Notice covers accounts and says personal information is not sold or rented, with no retention period for API or account data. The MCP addendum states 90 days for logs (15 of 30). No deprecation policy. The terms let the Bank change or discontinue the API at any time, and version 2 arrived with a dated notice (2 of 20). Google Analytics, Microsoft Clarity and YouTube are named, other contractors only by type, with no data locations (8 of 20). Total 37.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).

The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.

Provenance checks not met in full (half of this category, computed from checked facts):

- Terms of service: read, states 5 of the 7 things a reader expects, and has 3 clauses that cost points (2.3 of 10)
- Privacy policy: read, states 4 of the 8 things a reader expects (7 of 10)
- Status page: not found (0 of 10)
- security.txt: not found (0 of 10)

## What we couldn't check

What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.

- unchecked: key management in the FRED account (deleting or regenerating a key, any usage view), which sits behind a login
- unchecked: an authenticated call. No key was requested, so response headers on 200 and 429 (such as Retry-After) were not seen
- unchecked: the launch date of the FRED MCP Connector. Its help page carries no date and no news post about it is in the 50-item RSS feed
- unchecked: presence of the MCP connector in the official MCP registry
- The MCP connector is a separate surface with its own account, terms section and privacy addendum. It is described on this listing and not graded. It may merit its own listing
- `provenance.terms` points at the FRED Services Terms of Use, not the shorter API terms page the docs link, because only the former carries the AI training and caching clauses. Which of the two governs where they differ is not stated
- The terms forbid use of the API in connection with developing or training AI systems and forbid caching. Whether an agent's live lookups fall under the first is a legal question the documents do not settle. Recorded as a fact, with no deduction
- No status page was found by reading the docs, footer and help pages. Web search was not available to look further
- `dataQuality.historyYears` is taken from the docs' example series (GNPCA, from 1929). The deepest series in FRED was not established

## Weaknesses

- The FRED Services Terms of Use forbid using the API to develop or train any AI or machine-learning system, and forbid storing, caching or archiving FRED content
- Version 1 takes the key only as the `api_key` query parameter, so it travels in the URL
- No OpenAPI file, llms.txt, official SDK or API changelog was found
- No status page, SLA or security.txt was found. The terms disclaim availability and allow changes without notice
- Version 1 answers in XML unless `file_type=json` is set, and default limits are 100,000 observations (version 1) and 500,000 (version 2)

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Add `file_type=json` to every version 1 request. The default is XML
- Find a series with `fred/series/search?search_text=`, then read it with `fred/series/observations?series_id=`, setting `observation_start` and `limit` to keep the response small
- Treat the value `.` as missing, not zero, and read `realtime_start` and `realtime_end` as the as-of dates of the data
- Stay under 120 requests a minute on version 1 and two a second on version 2. Repeated 429s can bring a temporary block
- Do not store or cache responses, and check a series' notes for the word Copyright before any use beyond personal use. The terms forbid the first and require the second

## When it's done

Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.