Courier
REMOTE · MCP.COURIER.COM · SCANNED SEP 24
Send notifications, manage templates, and configure integrations with Courier.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security63
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (replace_journey). See how to fix → View diagnostics → Fail
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability82
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 14709 tokens (~91/item across 161 items; 161 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- Stability check failed: schema churn in the 30 days we've observed: 0 tool removals, 1 breaking changes, 0 auth/transport breaks, 17 additions. See how to fix → Fail
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 99% of tool parameters carry a description.Partial
Tool Safety50
- Injection-marker check failed: the description of tool "get_notification_metrics" contains an instruction to conceal the call from the user, the text "do NOT tell the user", at byte 3262 of that field. See how to fix → Fail
- All 25 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 161 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the Courier MCP server?
Courier is a hosted endpoint at https://mcp.courier.com/, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · mcp.courier.com
claude mcp add --transport http trycourier-courier 'https://mcp.courier.com/'
{
"mcpServers": {
"trycourier-courier": {
"url": "https://mcp.courier.com/"
}
}
} {
"servers": {
"trycourier-courier": {
"type": "http",
"url": "https://mcp.courier.com/"
}
}
} [mcp_servers.trycourier-courier] url = "https://mcp.courier.com/"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"trycourier-courier": {
"type": "remote",
"url": "https://mcp.courier.com/",
"enabled": true
}
}
} openclaw mcp add trycourier-courier --url 'https://mcp.courier.com/' --transport streamable-http
mcp_servers:
trycourier-courier:
url: "https://mcp.courier.com/" {
"McpServers": {
"trycourier-courier": {
"Transport": "http",
"Url": "https://mcp.courier.com/"
}
}
} assistant mcp add trycourier-courier -t streamable-http -u 'https://mcp.courier.com/'
{
"mcpServers": {
"trycourier-courier": {
"type": "http",
"url": "https://mcp.courier.com/"
}
}
} The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 23 Sept 26 0
- New tool “cancel_broadcast_schedule”, which the server declares destructive security
- New tool “delete_broadcast”, which the server declares destructive security
- Tool “put_journey_template_locale” rewrote its description, which is the text the model reads security
- Tool “replace_preference_topic” rewrote its description, which is the text the model reads security
- Schema quality: 13327 → 14709 ▼ functional
- New tool “create_broadcast” functional
- New tool “duplicate_broadcast” functional
- New tool “get_broadcast” functional
- New tool “get_broadcast_content” functional
- New tool “get_journey_run” functional
- New tool “list_broadcasts” functional
- New tool “list_journey_run_steps” functional
- New tool “list_journey_runs” functional
- New tool “put_broadcast_content” functional
- New tool “release_user_digest” functional
- New tool “rename_broadcast” functional
- New tool “schedule_broadcast” functional
- New tool “send_broadcast” functional
- New tool “trace_message” functional
- “create_preference_topic” added an optional parameter “digest” cosmetic
- “replace_preference_topic” added an optional parameter “digest” cosmetic
- “update_user_preference_topic” added an optional parameter “digest_schedule_id” cosmetic
- “update_user_preference_topic” added an optional parameter “tenant_id” cosmetic
- “put_journey_template_locale” reworded the description of “journey_id” cosmetic
- “put_journey_template_locale” reworded the description of “notification_id” cosmetic
- “put_journey_template_locale” reworded the description of “state” cosmetic
- 16 Sept 26 0
- Tool “create_journey_template” rewrote its description, which is the text the model reads security
- Tool “create_notification” rewrote its description, which is the text the model reads security
- Tool “put_notification_content” rewrote its description, which is the text the model reads security
- Tool “put_notification_element” rewrote its description, which is the text the model reads security
- Tool “put_notification_locale” rewrote its description, which is the text the model reads security
- Tool “replace_notification” rewrote its description, which is the text the model reads security
- “create_journey_template” reworded the description of “journey_id” cosmetic
- “create_notification” reworded the description of “state” cosmetic
- “get_journey” reworded the description of “journey_id” cosmetic
- “get_journey_template” reworded the description of “journey_id” cosmetic
- “get_journey_template” reworded the description of “notification_id” cosmetic
- “get_journey_template_content” reworded the description of “journey_id” cosmetic
- “get_journey_template_content” reworded the description of “notification_id” cosmetic
- “get_notification” reworded the description of “notification_id” cosmetic
- “get_notification” reworded the description of “version” cosmetic
- “get_notification_content” reworded the description of “notification_id” cosmetic
- “get_notification_draft_content” reworded the description of “notification_id” cosmetic
- “get_user_preferences” reworded the description of “tenant_id” cosmetic
- “list_journey_templates” reworded the description of “cursor” cosmetic
- “list_journey_templates” reworded the description of “journey_id” cosmetic
- “list_journeys” reworded the description of “cursor” cosmetic
- “list_journeys” reworded the description of “version” cosmetic
- “list_messages” reworded the description of “archived” cosmetic
- “list_messages” reworded the description of “cursor” cosmetic
- “list_notifications” reworded the description of “cursor” cosmetic
- “list_providers” reworded the description of “cursor” cosmetic
- “put_journey_template_content” reworded the description of “elements” cosmetic
- “put_journey_template_content” reworded the description of “journey_id” cosmetic
- “put_journey_template_content” reworded the description of “notification_id” cosmetic
- “put_notification_content” reworded the description of “notification_id” cosmetic
- “put_notification_content” reworded the description of “state” cosmetic
- “put_notification_content” reworded the description of “version” cosmetic
- “put_notification_element” reworded the description of “element_id” cosmetic
- “put_notification_element” reworded the description of “notification_id” cosmetic
- “put_notification_element” reworded the description of “state” cosmetic
- “put_notification_locale” reworded the description of “notification_id” cosmetic
- “put_notification_locale” reworded the description of “state” cosmetic
- “replace_journey” reworded the description of “journey_id” cosmetic
- “replace_notification” reworded the description of “notification_id” cosmetic
- “replace_notification” reworded the description of “state” cosmetic
- 15 Sept 26 −3
- Injection markers: pass → fail ▼ security
- New tool “get_notification_metrics” functional
- 4 Sept 26 +1
- Stability: pass → fail ▼ security
- A breaking change shipped without a version bump: still 1.3.7 ▼ security
- Tool “create_journey” rewrote its description, which is the text the model reads security
- Tool “create_journey_template” rewrote its description, which is the text the model reads security
- Tool “create_notification” rewrote its description, which is the text the model reads security
- Tool “invoke_automation_template” rewrote its description, which is the text the model reads security
- Tool “invoke_journey” rewrote its description, which is the text the model reads security
- Tool “list_automations” rewrote its description, which is the text the model reads security
- Tool “list_journeys” rewrote its description, which is the text the model reads security
- Tool “replace_journey” rewrote its description, which is the text the model reads security
- Tool “send_message” rewrote its description, which is the text the model reads security
- Tool “send_message_template” rewrote its description, which is the text the model reads security
- Tool “send_message_to_list” rewrote its description, which is the text the model reads security
- Tool “update_translation” rewrote its description, which is the text the model reads security
- Tool “bulk_subscribe_to_list” is now declared destructive security
- Tool “update_provider” is now declared destructive security
- “replace_tenant_template” made “content” required, so existing callers break ▼ functional
- Destructive annotations: All 23 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation. functional
- “create_or_update_tenant” reworded the description of “default_preferences” cosmetic
- “replace_journey” reworded the description of “nodes” cosmetic
- “replace_tenant_template” reworded the description of “channels” cosmetic
- “replace_tenant_template” reworded the description of “content” cosmetic
- “replace_tenant_template” reworded the description of “providers” cosmetic
- “replace_tenant_template” reworded the description of “routing” cosmetic
- “update_audience” reworded the description of “filter” cosmetic
- 26 Aug 26 81
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Aug 26 0
- Stability: 0.97 → pass security
- 20 Aug 26 0
- Tool “create_journey” rewrote its description, which is the text the model reads security
- Tool “create_journey_template” rewrote its description, which is the text the model reads security
- Tool “put_journey_template_content” rewrote its description, which is the text the model reads security
- Tool “replace_journey” rewrote its description, which is the text the model reads security
- Tool “put_journey_template_content” is now declared destructive security
- Tool “replace_journey” is now declared destructive security
- “create_journey” reworded the description of “state” cosmetic
- “create_journey_template” reworded the description of “state” cosmetic
- “put_journey_template_content” reworded the description of “state” cosmetic
- “replace_journey” reworded the description of “state” cosmetic
- 11 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 24 Sept 2026 · Probed https://mcp.courier.com
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=mcp.courier.com | CN=WE1,O=Google Trust Services,C=US | 9 Aug 2026 | 7 Nov 2026 | ECDSA 256 | ECDSA-SHA256 | df2aea7fc821556213cbc21276951523 |
| SANs: mcp.courier.com | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of mcp.courier.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| com. | present | 19718 | 13 | Verified |
| courier.com. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=15552000; includeSubDomains |
| content-security-policy | default-src 'self';base-uri 'self';font-src 'self' https: data:;form-action 'self';frame-ancestors 'self';img-src 'self' data:;object-src 'none';script-src 'self';script-src-attr 'none';style-src 'self' https: 'unsafe-inline';upgrade-insecure-requests |
| x-content-type-options | nosniff |
| x-frame-options | SAMEORIGIN |
| referrer-policy | no-referrer |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://mcp.courier.com | Verified | 200 | |
| http (plaintext) | http://mcp.courier.com | HTTPS enforced | 301 | https://mcp.courier.com/ |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
subscribe_user_to_lists ~50
Subscribe a user to one or more lists. Creates lists that do not exist.
| Name | Type | Req | Description |
|---|---|---|---|
| lists | array | yes | Array of lists to subscribe to |
| user_id | string | yes | The user ID |
No output schema declared.
No examples provided.
trace_message ~172
Trace delivery in one call. Give EXACTLY ONE of message_id (a single message) or trace_id (the metadata.trace_id set on a send, which can span several messages). Returns each matching message with its event history, which carries the status reason when a message is undeliverable. Set include_output to also return the rendered content each provider received.
| Name | Type | Req | Description |
|---|---|---|---|
| include_output | boolean | – | Also return rendered content per provider. Off by default, since rendered email can be large. |
| limit | integer | – | Max messages to trace for a trace_id. Defaults to 10. |
| message_id | string | – | A message id, as returned by send. Mutually exclusive with trace_id. |
| trace_id | string | – | The metadata.trace_id set on the send. Mutually exclusive with message_id. |
No output schema declared.
No examples provided.
track_inbound_event ~99
Track an inbound event that can trigger automations. Requires event name, messageId (for deduplication), and properties.
| Name | Type | Req | Description |
|---|---|---|---|
| event | string | yes | The event name (appears as trigger in Automation Trigger node) |
| messageId | string | yes | Unique ID for deduplication (returns 409 if not unique) |
| properties | object | yes | Event properties payload |
| userId | string | – | User ID associated with the event |
No output schema declared.
No examples provided.
unsubscribe_user_from_list ~42
Unsubscribe a user from a list.
| Name | Type | Req | Description |
|---|---|---|---|
| list_id | string | yes | The list ID |
| user_id | string | yes | The user ID to unsubscribe |
No output schema declared.
No examples provided.
update_audience ~142
Create or update an audience with a filter definition.
| Name | Type | Req | Description |
|---|---|---|---|
| audience_id | string | yes | The audience ID |
| description | string | – | Description |
| filter | – | – | Audience membership filter. Either a single condition ({ operator, path, value }) or a group ({ operator: "AND" | "OR", filters: [...] }) nesting to any depth. Example: { "operator": "AND", "filters"… |
| name | string | – | Display name |
No output schema declared.
No examples provided.
update_brand ~64
Replace an existing brand with new values.
| Name | Type | Req | Description |
|---|---|---|---|
| brand_id | string | yes | The brand ID to update |
| name | string | yes | Brand display name |
| settings | object | – | Brand settings (colors, email, inapp) |
| snippets | object | – | Brand snippets |
No output schema declared.
No examples provided.
update_notification_checks ~54
Update check statuses for a notification submission.
| Name | Type | Req | Description |
|---|---|---|---|
| checks | array | yes | Checks to update |
| notification_id | string | yes | The notification template ID |
| submission_id | string | yes | The submission ID for the checks resource |
No output schema declared.
No examples provided.
update_provider ~106
Replace an existing provider configuration. Full replacement — retrieve current config with get_provider first; omitted optional fields are cleared. Changing API keys or settings affects live delivery if this integration is in use.
| Name | Type | Req | Description |
|---|---|---|---|
| alias | string | – | Short alias |
| provider | string | yes | Provider key (must match existing; changing provider type is not supported) |
| provider_id | string | yes | The provider configuration ID |
| settings | object | – | Provider-specific settings |
| title | string | – | Display name |
No output schema declared.
No examples provided.
update_tenant_preference ~216
Set the default notification preference for a subscription topic on a tenant. This controls tenant-level defaults — it does NOT set per-user preferences (use the user preferences API for that). The topic_id must already exist as a subscription topic in the workspace; a 404 means the topic has not been created yet. Example: { tenant_id: "acme", topic_id: "marketing-updates", status: "OPTED_IN", has_custom_routing: true, custom_routing: ["email", "push"] }.
| Name | Type | Req | Description |
|---|---|---|---|
| custom_routing | array | – | Default channels when has_custom_routing is enabled |
| has_custom_routing | boolean | – | When true, use custom_routing instead of template defaults |
| status | string | yes | Subscription status for the topic |
| tenant_id | string | yes | The tenant ID |
| topic_id | string | yes | The subscription topic ID — must already exist in the workspace. A 404 response means the topic does not exist; create it in the Preferences Editor first. |
No output schema declared.
No examples provided.
update_translation ~80
Create or update a translation for a specific locale. API reference: https://www.courier.com/docs/api-reference/translations/update-translations-by-locale.
| Name | Type | Req | Description |
|---|---|---|---|
| body | string | yes | Translation content (PO file format) |
| domain | string | – | Translation domain |
| locale | string | yes | Locale code (e.g. en_US, fr_FR) |
No output schema declared.
No examples provided.
update_user_preference_topic ~144
Update a user's preference for a specific subscription topic (opt in, opt out, or set channel preferences).
| Name | Type | Req | Description |
|---|---|---|---|
| custom_routing | array | – | Custom channel routing order |
| digest_schedule_id | string|null | – | Put the user on one of the topic's digest schedules. Pass null to clear their choice and fall back to the default schedule. |
| has_custom_routing | boolean | – | Whether custom channel routing is set |
| status | string | yes | Preference status |
| tenant_id | string | – | Update the preference for this tenant context only |
| topic_id | string | yes | The subscription topic ID |
| user_id | string | yes | The user ID |
No output schema declared.
No examples provided.
What is the Courier MCP server?
Courier is an MCP server listed in the public MCP registry as io.github.trycourier/courier. Send notifications, manage templates, and configure integrations with Courier. This page covers its hosted endpoint (https://mcp.courier.com).
Is the Courier MCP server safe to use?
Courier scores 79 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Courier MCP server expose?
Courier exposes 161 tools: list_messages, get_message, get_message_content, get_message_history, list_notifications, and 156 more. Their descriptions and schemas cost roughly 14,709 tokens of context every time the server is loaded.
Does the Courier MCP server require authentication?
No. We connected to Courier without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Courier MCP server still maintained?
Courier is still listed as active in the MCP registry. We last reached this channel on 24 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.