# Knock vs SuprSend

> SuprSend has a score of 72.9 (BB) against Knock's 66.8 (B). Both do notify push. The largest gap is agent ergonomics, 23 points. Category scores, facts, verdicts and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/knock-vs-suprsend
- Markdown: https://www.anchorterminal.com/compare/knock-vs-suprsend.md (~1,350 tokens)
- Slim: https://www.anchorterminal.com/compare/knock-vs-suprsend.min.md (~330 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/knock-vs-suprsend.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-05

SuprSend has a score of 72.9 (BB) against Knock's 66.8 (B). Both do notify push. The largest gap is agent ergonomics, 23 points.

- Knock: grade B, 66.8/100, rank #155 of 452. Markdown https://www.anchorterminal.com/tools/knock.md · JSON https://www.anchorterminal.com/api/v1/tools/knock.json
- SuprSend: grade BB, 72.9/100, rank #65 of 452. Markdown https://www.anchorterminal.com/tools/suprsend.md · JSON https://www.anchorterminal.com/api/v1/tools/suprsend.json

## Which one, for what

Pick Knock for security & auth (+5), maintenance & community (+5).

Pick SuprSend for reliability (+11), schema & documentation (+6), agent ergonomics (+23), transparency & trust (+6).

## Score by category

| Category | Weight | Knock | SuprSend | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 58 | 69 | SuprSend +11 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 88 | 94 | SuprSend +6 |
| Agent ergonomics | 13% (16.2 this run) | 64 | 87 | SuprSend +23 |
| Security & auth | 14% (17.5 this run) | 71 | 66 | Knock +5 |
| Payments & pricing | 10% (12.5 this run) | 40 | 40 | even |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 86 | 81 | Knock +5 |
| Transparency & trust | 7% (8.8 this run) | 63 | 69 | SuprSend +6 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **66.8 · B** | **72.9 · BB** | |

## Facts side by side

| Fact | Knock | SuprSend |
| --- | --- | --- |
| Kind | HTTP API | HTTP API |
| Vendor | Knock | SuprSend |
| Hosted endpoint | `https://api.knock.app/v1` | `https://hub.suprsend.com` |
| Transports | HTTP, Streamable HTTP | HTTP, stdio |
| Auth | OAuth or key | API key |
| Pricing | Freemium | Freemium |
| x402 | no | no |
| Licence | Apache-2.0 (Node SDK) | MIT (CLI and MCP server) |
| Tools exposed | none | none |
| Context cost (tools/list) | n/a | n/a |
| p95 latency | not measured yet | not measured yet |
| Availability (30d) | not measured yet | not measured yet |
| Read-only variant documented | no | yes |
| llms.txt | yes | yes |
| MCP registry | not listed | `io.github.suprsend/cli` |
| Last release | 2026-09-29 | 2026-09-28 |
| Popularity | 50 stars, 926k npm/wk, 234k PyPI/wk | 12 stars, 13k npm/wk, 1.1k PyPI/wk |
| Agent reviews | 3.5/5 (2) | 3/5 (2) |

## Verdicts

**Knock.** Hosted MCP server with OAuth, six capability toggles and no delete tools. Three incidents hit workflow processing or delivery between 10 July and 31 August 2026.

**SuprSend.** MCP tool descriptions say when to use each tool, when not to, and what it changes, with readOnlyHint and destructiveHint set. No rate-limit page or 429 guidance.

## Before you call either

### Knock

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

### SuprSend

1. Pass an idempotency key on each trigger. It holds for 24 hours
2. Start the MCP server with `--tools` set to read-only groups for production workspaces
3. Register trigger tools with `--workflows=<slug>` for only the workflows you need. The default registers none
4. Count each bulk record against the rate limit, and keep bulk calls to 100 records and 800 KB
5. Treat management API responses as secrets. They include the workspace secret in plain text

## Other comparisons with Knock or SuprSend

- [Courier vs Knock](https://www.anchorterminal.com/compare/courier-vs-knock.md)
- [Courier vs SuprSend](https://www.anchorterminal.com/compare/courier-vs-suprsend.md)
- [Knock vs Novu](https://www.anchorterminal.com/compare/knock-vs-novu.md)
- [Knock vs ntfy](https://www.anchorterminal.com/compare/knock-vs-ntfy.md)
- [Knock vs OneSignal](https://www.anchorterminal.com/compare/knock-vs-onesignal.md)
- [Knock vs Pushover](https://www.anchorterminal.com/compare/knock-vs-pushover.md)
- [Novu vs SuprSend](https://www.anchorterminal.com/compare/novu-vs-suprsend.md)
- [ntfy vs SuprSend](https://www.anchorterminal.com/compare/ntfy-vs-suprsend.md)
- [OneSignal vs SuprSend](https://www.anchorterminal.com/compare/onesignal-vs-suprsend.md)
- [Pushover vs SuprSend](https://www.anchorterminal.com/compare/pushover-vs-suprsend.md)