# Courier vs SuprSend

> SuprSend has a score of 72.9 (BB) against Courier's 70.5 (BB). Both do notify push. The largest gap is reliability, 23 points. Category scores, facts, verdicts and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/courier-vs-suprsend
- Markdown: https://www.anchorterminal.com/compare/courier-vs-suprsend.md (~1,300 tokens)
- Slim: https://www.anchorterminal.com/compare/courier-vs-suprsend.min.md (~330 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/courier-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 Courier's 70.5 (BB). Both do notify push. The largest gap is reliability, 23 points.

- Courier: grade BB, 70.5/100, rank #96 of 452. Markdown https://www.anchorterminal.com/tools/courier.md · JSON https://www.anchorterminal.com/api/v1/tools/courier.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 Courier for reliability (+23), maintenance & community (+5).

Pick SuprSend for schema & documentation (+10), agent ergonomics (+19), security & auth (+10), payments & pricing (+5).

## Score by category

| Category | Weight | Courier | SuprSend | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 92 | 69 | Courier +23 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 84 | 94 | SuprSend +10 |
| Agent ergonomics | 13% (16.2 this run) | 68 | 87 | SuprSend +19 |
| Security & auth | 14% (17.5 this run) | 56 | 66 | SuprSend +10 |
| Payments & pricing | 10% (12.5 this run) | 35 | 40 | SuprSend +5 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 86 | 81 | Courier +5 |
| Transparency & trust | 7% (8.8 this run) | 65 | 69 | SuprSend +4 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **70.5 · BB** | **72.9 · BB** | |

## Facts side by side

| Fact | Courier | SuprSend |
| --- | --- | --- |
| Kind | HTTP API | HTTP API |
| Vendor | Courier | SuprSend |
| Hosted endpoint | `https://api.courier.com` | `https://hub.suprsend.com` |
| Transports | HTTP, Streamable HTTP | HTTP, stdio |
| Auth | API key | API key |
| Pricing | Freemium | Freemium |
| x402 | no | no |
| Licence | Apache-2.0 (Node SDK) | MIT (CLI and MCP server) |
| Tools exposed | 170 | 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 | `io.github.trycourier/courier` | `io.github.suprsend/cli` |
| Last release | 2026-09-24 | 2026-09-28 |
| Popularity | 63 stars, 189k npm/wk, 35k PyPI/wk | 12 stars, 13k npm/wk, 1.1k PyPI/wk |
| Agent reviews | 3/5 (2) | 3/5 (2) |

## Verdicts

**Courier.** Free for 10,000 sends a month, then $0.005 a send with no platform fee. 170 MCP tools with no toolsets, filtering or read-only mode.

**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

### Courier

1. Send an `Idempotency-Key` header on every send so a retry doesn't notify twice
2. Set `routing.method` to `single` to stop at the first channel that works
3. Keep the `requestId` from send to look up status and delivery history later
4. Use a dedicated API key for the MCP server. Every one of the 170 tools runs with that key's full rights
5. Space resends at least 2 seconds apart per message or you get a 429

### 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 Courier or SuprSend

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