Knock by Knock

# Fix list: Knock

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/knock, the October 2026 research run, assessed 1 October 2026. Grade B, 66.8 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 Knock: 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, 58 out of 100, up to 8.4 more on the total

Why it scored 58: Statuspage at status.knock.app (20). Eight entries since 10 July 2026, and three of them hit core delivery. A "Workflow engine outage" on 10 July covering the API, webhooks and notification delivery, then "Workflow processing and message delivery errors" on 16 July and again on 31 August. The feed gives no durations, so we can't say how long each lasted, and score between one major and several (5). Limits published in five tiers from 1 to 1,000 requests a second, scoped per environment (15). Over-limit calls get 429, but we found no Retry-After header or backoff guidance, only an `Idempotency-Key` on trigger with a 24-hour window (8). No SLA on the pricing page (0). The trigger API is generally available (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.

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

Why it scored 40: No x402, MPP or L402 (0). Starter overage at $0.005 a message and agent credits at $0.01, published without login (20). Developer plan free for 10,000 messages a month, and the pricing page says Knock gets in touch about billing only if you go over, so no card up front (20). A person signs up in the dashboard (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.

## 3. Agent ergonomics, 64 out of 100, up to 5.9 more on the total

Why it scored 64: The agent toolkit defines 46 tools, and the hosted server splits its tools into six toggles with debug, data management and docs off by default, so a session starts smaller (5 plus 10 for the toggles). We didn't check pagination or field selection in this run (10). Errors are documented only as status classes plus an error-codes page we couldn't read (8). `Idempotency-Key` on `POST /workflows/:key/trigger` only, 24 hours, up to 255 characters, rejecting a reused key with different parameters, and a `cancellation_key` to stop delayed runs. The MCP server ships no delete tools on purpose (16). A trigger needs a workflow key and recipients, with official SDKs for Node and Python among others (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.

## 4. Security & auth, 71 out of 100, up to 5.1 more on the total

Why it scored 71: The MCP server signs in with OAuth or a `knock_st_` service token. Secret API keys are per environment, and client feeds use a public key plus signed user tokens. Service tokens inherit the creator's privileges, have full management API access and no expiry, but revoke immediately (22). No delete tools in the MCP server, data management off by default and an OAuth consent screen, though a service-token session skips consent and turns every capability on. The toolkit has human-in-the-loop helpers (15). Tools return message content and user data with no prompt-injection guidance found (5). Audit logs record management API changes with the token as author, and every message has delivery logs and events (14). The security page lists SOC 2 Type 2, HIPAA, GDPR and CCPA, third-party pen tests and a disclosure process at security@knock.app. No bug bounty found, and no security.txt per the 30 September check (15).

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.

## 5. Transparency & trust, 63 out of 100, up to 3.2 more on the total

Made of editorial 39, provenance 86.

Why it scored 63: Closed service under published terms, with Apache-2.0 SDKs and an MIT agent toolkit (15). A data processing addendum and data retention docs are published, per the 30 September check, and we didn't reread them (16). No deprecation or API versioning policy found (3). The security page names no subprocessors or hosting regions (5).

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: knock.app, registered 2020-08-28 (6 years) (11 of 15)
- security.txt: not found (0 of 10)

## 6. Schema & documentation, 88 out of 100, up to 2 more on the total

Why it scored 88: OpenAPI at docs.knock.app/openapi.json for the API, per the 30 September check, plus a separate management API reference (25). llms.txt with more than 500 Markdown entries (10). The open-source agent toolkit's tool descriptions say what each tool does, when to use it and what it returns, for example `trigger_workflow` (18). Zod schemas with required fields, though workflow `data` and `tenant` are free-form records (12). Examples on every reference page, but the errors page gives only status classes, and we couldn't read the list on the error-codes page (8). /v1 paths, a public changelog and release-please SDK changelogs (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. Maintenance & community, 86 out of 100, up to 1.2 more on the total

Why it scored 86: knock-node v1.36.0 on 29 September 2026 (30). Four SDK releases since 3 July (14 and 16 July, 3 and 29 September) plus changelog entries for the Claude connector on 28 August and other agent plugins in September per the 30 September check (20). A closed service with a dated changelog and a security contact. We didn't test support response (11). Current official SDKs (15). The Node SDK runs CI with release-please, and the agent toolkit moved to npm trusted publishing on 9 September (10).

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.

## 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.

- How long the 10 July, 16 July and 31 August 2026 incidents lasted, which the status feed doesn't say
- unchecked: the contents of the error-codes page, which didn't load in full
- The exact tool count on the hosted MCP server, which may differ from the 46 tools in the open-source toolkit
- unchecked: pagination and field selection on list endpoints

## Weaknesses

- Three incidents hit workflow processing or delivery between 10 July and 31 August 2026
- No SLA, Retry-After header or backoff guidance found
- Service tokens carry the creator's full privileges with no expiry, and skip MCP consent
- Starter jumps from free to $250 a month
- Email, SMS and push go through providers you configure and pay for separately

## 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.

- Create the workflow in the dashboard or through the MCP server before you trigger it. Triggers reference it by key
- Send an `Idempotency-Key` on every trigger. It holds 24 hours and only the trigger endpoint accepts it
- Pass a `cancellation_key` when you trigger so a later cancel call can stop a delayed or batched run
- Use a service token only for headless MCP sessions, since it skips consent and enables every capability
- Keep test and production apart. Rate limits and keys are scoped to an environment

## What the review panel asked for

- Expire service tokens
- written deprecation policy

## 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.