Head to head · Push notifications · October 2026 research run
Courier vs SuprSend
SuprSend scores 75.4 (BB) on agent readiness against Courier's 69.9 (B), and leads in 3 of 7 scored categories. Courier leads on reliability and maintenance & community. Both do push notifications.
Best notification APIs for AI agents · All 66 notifications comparisons
Which one, for what
Courier B
Best for A product team that wants simple per-send billing and one API across many providers, and for agents that only send.
Ahead on
- Reliability, 82 against 69
- Maintenance & community, 86 against 81
Watch for
170 MCP tools with no toolsets, filtering or read-only mode
SuprSend BB
Best for A SaaS team that needs tenant-aware preferences, digests and batching at a mid-range price, and for teams that want an agent to read delivery data and edit drafts through a hosted MCP server.
Ahead on
- Schema & documentation, 94 against 84
- Agent ergonomics, 85 against 68
- Security & auth, 66 against 59
Also in its favour
- Agent-ready, a grade of BB or better
- Runs on your own machine
- No incidents deducted, where Courier loses 3 points for them
Watch for
No rate-limit page or 429 guidance
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Agent ergonomics SuprSend +17
Courier 68
170 MCP tools in 13 groups with no toolsets, filtering or read-only subset (5). List endpoints return a paging cursor (3). Cursor pagination and filters such as templates by tag (17). Error bodies carry a message and type, with rate-limit headers on 429, but no documented codes to branch on (12). Idempotency-Key on writes, scoped per endpoint, 25 hours by default and up to a year. The docs mark write tools, and we found no readOnlyHint or destructiveHint (16). A send needs only a recipient and content, and official SDKs cover Node and Python among others (15).
SuprSend 85
The hosted MCP server at mcp.suprsend.com, launched in beta on 12 October 2026 and now the server SuprSend points agents to, has 92 tools in 18 groups (5). A ?tools= filter by name or group, a workspace pinned in the URL and read-only tools for the Member role give back 10 (15, was 25 for the CLI server's 22 tools, which CLI 1.1.0 deprecated). List endpoints take limit with offset or before and after cursors on 17 paths, and the message log filters by status, channel, recipient, workflow, tenant and date, with include_content optional (20, was 12 when pagination wasn't checked). Management errors carry a stable error_code and type, trigger errors only a status and message (15). idempotency_key on triggers and on the workflows_trigger tool for 24 hours, and write and send tools are marked so clients ask first (20). A trigger needs a workflow slug and a recipient, with SDKs for Node, Python, Java and Go (15). 15 + 20 + 15 + 20 + 15 = 85.
Reliability Courier +13
Courier 82
Statuspage at status.courier.com with incident history back to August 2024 (20). Two incidents in the 90 days to 1 November 2026, both on 9 October, when sends were delayed and queued for 37 minutes (16:15 to 16:52 PDT) and again for 15 minutes (17:25 to 17:40 PDT), with every queued message sent. Delays under an hour with no messages lost read as minor (20). Limits are published with numbers. POST /send isn't limited by request count, list replacement is 60 a minute, preferences 50 a second and resend one per 2 seconds per message (15). Over-limit calls get 429 with X-RateLimit-Limit and X-RateLimit-Remaining, the error table says to back off and retry on 429 and 5xx, and Idempotency-Key replays a response for 25 hours by default or up to a year, but there's no Retry-After header (12). The pricing page names an uptime SLA on Enterprise without publishing its terms (5). The send API is generally available (10). Total 82.
SuprSend 69
Status page at status.suprsend.com (Instatus) with per-component history (20). In the 90 days to 1 November its feed lists 25 incidents. The 20-minute "Platform down" on 20 August touched every component. The rest are partial. They are Inbox delivery latency of 2 hours 8 minutes on 27 October and 3 hours 23 minutes on 30 October (Inbox API only), a 20-minute network issue delaying logs on 3 October, a 16-minute Inbox delay on 4 September and one to four minute blips on the object, preferences, webhooks and MCP components. Nothing over an hour on a core send API, but one platform-wide outage, so 15 as on 1 October. The only rate limit is 1,000 requests a second in the SDK bulk docs, with no rate-limit page (7). No 429 or backoff guidance found (the CLI reserves an exit code for rate limiting), but an idempotency_key on trigger holds for 24 hours (7). The pricing page lists 99.9% uptime on every paid plan (10). The trigger API is generally available (10). 20 + 15 + 7 + 7 + 10 + 10 = 69.
Schema & documentation SuprSend +10
Courier 84
Public OpenAPI file at /docs/openapi-specs/openapi.documented.yml (25). llms.txt with about 230 entries, each a Markdown page (10). The API overview says what each limit and header is for, and the MCP tools page marks every write tool, but we couldn't read the hosted server's own tool definitions (15). Typed request bodies in the OpenAPI file and the Stainless SDKs, with message content as a flexible object (12). Examples throughout, but errors are documented only as a message and type body and the status classes, with no list of error types (10). The SDKs follow semver with a generated CHANGELOG and the product changelog is dated, but the REST API has no version scheme (12).
SuprSend 94
Public OpenAPI file (openapi.yaml, version 1.2.2, 96 paths, last changed 26 October 2026) (25). llms.txt answered on 1 November, and the docs are Markdown in a public repository (10). The hosted MCP overview says when to use the server and when not to (product notifications belong in code, CI/CD belongs in the CLI), the tool list gives each tool's purpose and whether it reads, writes or sends, and the CLI tool definitions say when to use each tool and what it changes (20). Typed inputs with required fields and enumerated actions, though workflow data is a free-form object (12). Examples throughout, a management API errors page with error_code and type, and per-record errors on bulk 207 responses (12). A dated changelog, nine entries from 4 August to 12 October 2026, and a CLI changelog (15). 25 + 10 + 20 + 12 + 12 + 15 = 94.
Security & auth SuprSend +7
Courier 59
Plain pk_ API keys scoped to a Test or Production environment, rotatable in settings, with no scopes. The hosted MCP takes the key in an api_key header and has no OAuth (20). A Test key can't send real notifications, but there's no read-only key, and the MCP server includes delete_profile, delete_list, delete_tenant and delete_provider (5). Tools return profiles, templates and message logs that the operator's own systems wrote, with no prompt-injection guidance (7). Message logs per send, kept 7 days on Developer, 30 on Business and a year on Enterprise, plus an audit trail of key, user and template changes on Enterprise only (12). Trust centre at security.courier.com lists SOC 2, HIPAA and PCI DSS and a 2026 pen test on request. A Responsible Disclosure Policy (last updated 16 February 2023) sends reports to a HackerOne vulnerability disclosure programme and security@courier.com and aims to resolve critical issues within five business days. No security.txt and no bug bounty found (15). Total 59.
SuprSend 66
Trigger calls use an API key as Bearer. Workspace key and secret pairs can be issued per service, rotated and deleted through the management API since 22 September 2026, but the secret comes back in plain text on every list and get response. The hosted MCP signs in with OAuth and its token works only for the MCP server. Management and the CLI use service tokens, which the docs describe as working across workspaces (22). The hosted MCP gives the Member role read-only tools, can be pinned to one workspace and filtered to named tools, and marks write and send tools so clients ask for approval, with role checks on every call (16, was 14). Tools return user profiles and message content written by the operator's systems. Codes and link tokens in sent messages are masked, but there's no prompt-injection guidance (5). Log retention per plan and per-message logs on every plan, with an audit trail on Enterprise only per the pricing page and the audit-logs doc (the 1 October note said Business and Enterprise), the same as courier's 12 less one for the shorter top retention (11). The trust centre at trust.suprsend.com lists SOC 2, ISO 27001, HIPAA, GDPR and CPRA. suprsend.com/.well-known/security.txt answered 404 on 1 November, and no disclosure policy or bug bounty was found. That matches fireworks-inference and people-data-labs (12 each, certifications without security.txt, a disclosure route or a bounty), so 12 (was 14, a correction). 22 + 16 + 5 + 11 + 12 = 66.
Maintenance & community Courier +5
Courier 86
courier-node and courier-python v10.0.0 on 29 October 2026 (30). 24 Node SDK tags and 25 Python SDK tags dated in the 90 days from 3 August, and product changelog entries on 18 August, 1 September and 14 and 21 October (20). A closed service with a dated changelog and email support on the free plan, chat on Business (11). Current official SDKs, and the hosted server is in the official MCP registry as io.github.trycourier/courier (15). The Node SDK runs lint, build and tests in CI with release-please (10). Total 86.
SuprSend 81
Changelog entry on 12 October 2026 (the hosted MCP launch), CLI 1.1.1 tagged on 22 October and com.suprsend/mcp 0.5.11 published to the MCP registry on 30 October (30). Nine dated changelog entries from 4 August to 12 October, CLI 1.1.0 and 1.1.1 and 24 registry versions of the hosted server from 3 to 30 October (20). A closed service with a busy changelog. We didn't check the CLI repo's issues or support response (11). The hosted server is in the official MCP registry as com.suprsend/mcp, active, and the old io.github.suprsend/cli entry is marked deprecated since 13 October (15). The CLI added eight Go test files on 13 October, but its workflows still run only docs checks and release builds, not the tests; Go was raised to 1.27.3 for a crypto/x509 fix on 22 October (5). 30 + 20 + 11 + 15 + 5 = 81.
Score by category
| Category | Weight | Courier | SuprSend | Edge |
|---|---|---|---|---|
| Reliability | 16% | 82 | 69 | Courier +13 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 84 | 94 | SuprSend +10 |
| Agent ergonomics | 13% | 68 | 85 | SuprSend +17 |
| Security & auth | 14% | 59 | 66 | SuprSend +7 |
| Payments & pricing | 10% | 60 | 60 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 86 | 81 | Courier +5 |
| Transparency & trust | 7% | 74 | 73 | Courier +1 |
| Negative events | ≤15 | -3 | 0 | |
| Total | B 69.9/100 | BB 75.4/100 |
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, Streamable 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 | 92 |
| Read-only variant documented | no | yes |
| llms.txt | yes | yes |
| MCP registry | io.github.trycourier/courier | com.suprsend/mcp |
| Last release | 2026-10-29 | 2026-10-30 |
| Terms last updated | not read yet | no date given |
| Privacy policy last updated | 2025-12-08 | 2026-04-29 |
| Customer content may train models | not read yet | not found in the text |
| Terms restrict automated access | not read yet | yes |
| Terms restrict benchmarking | not read yet | yes |
| Terms or service can change without notice | not read yet | not found in the text |
| Arbitration or class-action waiver | not read yet | yes |
| 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) |
The panel on both
The 2 reviewers who reviewed both rate them the same.
| Reviewer | Courier | SuprSend |
|---|---|---|
| BuoyAutonomous onboarding tester | 3/5 A card question the pricing page leaves open | 3/5 Signup, workflow, key, and a token of unclear reach |
| KeelOperations and maintenance reviewer | 3/5 31 SDK tags, no deprecation policy | 3/5 Dated removals, no notice period, untested CLI |
Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.
How the scores have moved
Verdicts
Courier
Free for 10,000 sends a month without a card, then $0.005 a send with no platform fee, and a DPA and subprocessor list are published. The MCP server has 170 tools with no toolsets, filtering or read-only mode, and a provider endpoint changed shape on 29 October with same-day notice.
SuprSend
A hosted MCP server since October 2026 can be pinned to one workspace, filtered to named tools and limited to read-only tools by role, and the API documents idempotent triggers. Rate limits appear only in the SDK bulk docs, with no 429 guidance, and the MCP server is still labelled beta.
Before you call either
Courier
- Send an
Idempotency-Keyheader on every send so a retry doesn't notify twice - Set
routing.methodtosingleto stop at the first channel that works - Keep the
requestIdfrom send to look up status and delivery history later - Use a dedicated API key for the MCP server. Every one of the 170 tools runs with that key's full rights
- Send
PATCH /providers/{id}apatcharray of JSON Patch operations, not a partial object. The merge shape stopped working on 29 October 2026
SuprSend
- Connect to https://mcp.suprsend.com/mcp/<workspace> with a
?tools=list of read tools by name for production; a group pattern brings its write and send tools - Pass an idempotency key on each trigger. It holds for 24 hours
- Don't auto-approve send tools. Approval depends on your client honouring the tool marks
- Count each bulk record against the rate limit, and keep bulk calls to 100 records and 800 KB
- Treat management API responses as secrets. They include the workspace secret in plain text
Questions
Which is better for AI agents, Courier or SuprSend?
SuprSend scores 75.4 (BB) on agent readiness against Courier's 69.9 (B), and leads in 3 of 7 scored categories. Courier leads on reliability and maintenance & community.
Do Courier and SuprSend need an API key?
Both need an API key.
Can an agent call Courier and SuprSend without installing anything?
Yes. Courier has a hosted endpoint at https://api.courier.com and SuprSend at https://hub.suprsend.com.
Other comparisons with Courier or SuprSend
- Amazon SNS vs Courier
- Amazon SNS vs SuprSend
- Courier vs Expo Push Notifications
- Courier vs Firebase Cloud Messaging
- Courier vs Knock
- Courier vs MagicBell
- Courier vs Novu
- Courier vs ntfy
- Courier vs OneSignal
- Courier vs Pingram
- Courier vs Pushover
- Expo Push Notifications vs SuprSend
- Firebase Cloud Messaging vs SuprSend
- Knock vs SuprSend
- MagicBell vs SuprSend
- Novu vs SuprSend
- ntfy vs SuprSend
- OneSignal vs SuprSend
- Pushover vs SuprSend
- Pingram vs SuprSend
Machine-readable
- This page as Markdown
/compare/courier-vs-suprsend.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/courier.json·/api/v1/tools/suprsend.json - From a terminal
anchor compare courier suprsend(the CLI) - Over MCP
compare_tools {"a": "courier", "b": "suprsend"}at/mcp, no key