folk API + MCP by folk

# Fix list: folk API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/folk, the October 2026 research run, assessed 1 October 2026. Grade C, 61 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 folk API + MCP: 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. Security & auth, 43 out of 100, up to 10 more on the total

Why it scored 43: REST keys are workspace Bearer keys with no scopes, and we found no rotation or expiry docs. The MCP server uses OAuth and gets the signed-in user's full access (17 of 30). No read-only mode. The MCP server can't delete records, only update them and remove group members, and the docs urge human confirmation of each step (10 of 20). A security best-practices page warns that untrusted tools and content can carry malicious instructions, and call transcripts only come back when the workspace's interaction privacy rules allow (9 of 15). No audit log found. Errors carry a `requestId` (2 of 15). security@folk.app in the privacy policy, TLS 1.2 and AES-256 stated. No SOC 2 or ISO 27001 found, no security.txt (404), no bug bounty (5 of 20).

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.

## 2. Reliability, 55 out of 100, up to 9 more on the total

Why it scored 55: Status page at status.folk.app runs on UptimeRobot and has a history view, but its data failed to load on two tries, so we couldn't see components (15 of 20). No readable incident history (5). One limit of 600 requests a minute per user across all endpoints, with default and burst policies (15). 429s carry a `details` object with the policy, limit, window and a `retryAfter` timestamp, and the API accepts an `Idempotency-Key` header for safe retries (15). No SLA found (0). REST is GA, but the MCP server has been in open beta since 1 July 2026 and the Interactions API since 17 August 2026 (5 of 10).

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.

## 3. Payments & pricing, 30 out of 100, up to 8.8 more on the total

Why it scored 30: No x402, MPP or L402 (0). Plan prices public, Standard $24 or $30, Premium $48 or $60 and Enterprise from $80 or $100 a member a month, with the REST API from Premium (10). Two-week trial with no card (20). A person signs up in a browser (0).

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.

## 4. Agent ergonomics, 70 out of 100, up to 4.9 more on the total

Why it scored 70: 38 MCP tools with no toolsets or read-only subset (5). REST lists take a limit (3 more, 8 of 25). Paginated lists, people and company filters, and notes search with date filters (18 of 20). Errors carry `code`, `message`, `documentationUrl`, `requestId` and, on a 429, `retryAfter` (20). `Idempotency-Key` on writes, the MCP docs mark each tool read-only, destructive or idempotent, and there are no MCP tools that delete records (18 of 20). Every call needs `X-API-Version`, and there's no official SDK (6 of 15).

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.

## 5. Maintenance & community, 60 out of 100, up to 3.5 more on the total

Why it scored 60: Newest changelog entry on 2026-09-15 (phone calls as interactions) (30). Nine dated entries since 3 July 2026 (20). Public changelog and support. We didn't test support (10 of 15). Not in the official MCP registry. The only folk entry, at folk.usefulapi.io, is a third party's. No official SDK (0). No packages to judge (0).

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. Schema & documentation, 91 out of 100, up to 1.5 more on the total

Why it scored 91: OpenAPI 3.1 spec per dated API version, 2025-06-09 (25). llms.txt with 61 links and Markdown pages (10). Each MCP tool has a one-line purpose and badges for read-only, destructive and idempotent. We read the docs page, not the server's own tools/list (13 of 20). Typed inputs in the spec (13 of 15). Error table with codes, examples and a `documentationUrl` on every error (15). Dated versions in `X-API-Version`, endpoints kept at least a year, 6 months' notice with `Deprecation` and `Sunset` headers, and a public changelog (15).

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.

## 7. Transparency & trust, 83 out of 100, up to 1.5 more on the total

Made of editorial 80, provenance 86.

Why it scored 83: Closed service. The terms of use don't name the company, while the privacy policy names Folk Inc. of Delaware (12 of 15). Privacy policy updated 18 September 2026 with retention spelled out (7 days from databases after deletion, 730 days from backups, 930 days from logs), a table of 24 processors and a promise not to train AI models on customer data (28 of 30). Written deprecation policy with a year's support and 6 months' notice, and the reminder endpoints carry a dated removal on 2027-02-13 (20). Processors listed with regions, and hosting on AWS in Ireland (20).

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):

- Domain age: folk.app, registered 2018-05-08 (8 years) (11 of 15)
- 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: status page incident history, which failed to load twice
- The 30 September check gave a last release of 2026-09-24, but the changelog's newest entry today is 2026-09-15
- Whether REST API keys can be rotated or expire, not stated in the authentication docs
- Whether the hosted MCP server sets `readOnlyHint` and `destructiveHint` in tools/list, as the docs' badges suggest

## Weaknesses

- MCP server in open beta since 1 July 2026
- REST API keys have no scopes and MCP gets the user's full access
- REST API only on Premium and Enterprise
- Status page history didn't load, so the incident record is unknown
- No SOC 2 or ISO 27001 found, and no security.txt

## 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.

- Send `X-API-Version: 2025-06-09` on every REST call
- Set an `Idempotency-Key` on creates, and treat a 409 `IDEMPOTENCY_REQUEST_IN_PROGRESS` as wait and retry
- On a 429, wait until `details.retryAfter`, and remember all your keys share one 600-a-minute budget
- Move off the reminder endpoints to tasks before their removal on 2027-02-13
- Expect some interaction content to be hidden by the workspace's privacy rules

## What the review panel asked for

- confirm hints in tools/list
- add toolsets
- scoped, expiring API keys
- a read-only MCP mode

## 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.