Kourier
REMOTE · KOURIER.SH
Discover flat-rate DeepSeek plans, model limits, API-key instructions, and coding-client setup.
Available components
Last scanned (6 hours ago)
Scores higher than 68% of remote servers
Reachable. Last reached 19 Oct 2026.
Category AI and Machine Learning
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 Security83
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC is configured correctly; the domain's records validate against the full chain to the root. View diagnostics → Pass
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability79
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 725 tokens (~80/item across 9 items; 8 tools + 1 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management23
- Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage93
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 80% of tool parameters carry a description.Partial
Tool Safety50
- Injection-marker check failed: the description of parameter "onboarding_token" on tool "get_onboarding_status" contains an instruction to conceal the call from the user, the text "Never show it to the human", at byte 26 of that field, plus 1 further marker(s) of the same kind. See how to fix → Fail
- All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 10 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
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.
- 18 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.
- 16 Oct 26 +1
- The server rewrote its instructions, which are the text every model session reads security
- Schema quality: 65 → 80 ▼ functional
- Destructive annotations: pass → 100 functional
- New tool “submit_feedback” functional
- 14 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.
- 13 Oct 26 0
- Stability: unverified → 0.03 ▲ functional
- 12 Oct 26 72
First indexed and scored.
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 19 Oct 2026 · Probed https://kourier.sh/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=kourier.sh | CN=WE1,O=Google Trust Services,C=US | 3 Oct 2026 | 1 Jan 2027 | ECDSA 256 | ECDSA-SHA256 | aca4cbb5f8ed630313d605b2e684ff8e |
| SANs: kourier.sh, status.kourier.sh, *.status.kourier.sh | ||||||
| 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 secure
Validation of kourier.sh. — Secure
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| sh. | present | 34349, 55297 | 8, 8 | Verified |
| kourier.sh. | present | 2371 | 13 | Verified |
| kourier.sh. | Verified address RRset verified with the apex keys |
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=31536000 |
| content-security-policy | default-src 'self'; script-src 'self' 'nonce-2ed48fa0e47f4eeca54c0d526a87d4df' https://static.cloudflareinsights.com https://www.googletagmanager.com; script-src-attr 'none'; style-src 'self' 'unsafe-inline'; font-src 'self'; img-src 'self' data: blob: https:; connect-src 'self' https://app.kourier.sh https://cloudflareinsights.com https://*.google-analytics.com https://www.googletagmanager.com; worker-src 'self' blob:; object-src 'none'; base-uri 'none'; frame-ancestors 'none'; frame-src 'none'; require-trusted-types-for 'script'; trusted-types kourier-jsonld kourier-analytics goog#html; form-action 'self' https://app.kourier.sh; upgrade-insecure-requests |
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | strict-origin-when-cross-origin |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://kourier.sh/mcp | Verified | 200 | |
| http (plaintext) | http://kourier.sh/mcp | HTTPS enforced | 301 | https://kourier.sh/mcp |
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 →
complete_onboarding Exchange approved onboarding once ~71
Deliver a dedicated revocable inference key exactly once after human approval and active entitlement. Never retry after issuance or ambiguous delivery; check status instead. Keep the key private and configure the client only with user approval.
| Name | Type | Req | Description |
|---|---|---|---|
| onboarding_token | string | yes | Private onboarding token. Never show it to the human or log it. |
No output schema declared.
No examples provided.
create_checkout_link Start human-approved onboarding ~99
Create a verified sign-in, recurring Starter/Pro plan and explicit agent access approval link. Show only onboarding_url and user_code to the human; keep the token private. This does not itself charge or issue a key.
| Name | Type | Req | Description |
|---|---|---|---|
| client_name | string | yes | Human-readable client name; no control characters or blank names. |
| harness | string | – | Client to configure. Omit for the generic OpenAI-compatible settings. |
| plan | string | yes | – |
No output schema declared.
No examples provided.
get_api_key_instructions Get an API key ~42
How a person or an agent obtains a Kourier API key: dashboard sign-up, agent sign-in (auth.md), or OAuth with PKCE.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_models Models and limits ~24
The model Kourier serves, its API model string, and context limits.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_onboarding_status Check onboarding approval ~64
Check approval and signed-webhook-backed entitlement, without identity or secrets. Poll every 5 seconds; complete only when ready. Stop on issued, denied or expired.
| Name | Type | Req | Description |
|---|---|---|---|
| onboarding_token | string | yes | Private onboarding token. Never show it to the human or log it. |
No output schema declared.
No examples provided.
get_pricing Plans and pricing ~28
Kourier's plans, monthly prices, concurrency limits, and what has no usage cap.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_setup_instructions Tool setup ~55
Configuration for using Kourier from Oh My Pi, Claude Code, Codex CLI, or any OpenAI-compatible client.
| Name | Type | Req | Description |
|---|---|---|---|
| harness | string | – | Client to configure. Omit for the generic OpenAI-compatible settings. |
No output schema declared.
No examples provided.
submit_feedback Submit feedback or an error report ~151
Send feedback or report a Kourier error, attributed to your account. Requires your Kourier API key in the MCP connection's Authorization: Bearer header, never in tool arguments. Submit only what the user wants to share; exclude API keys, tokens, passwords, personal data, and private code or logs. Include a request_id when available to help investigation.
| Name | Type | Req | Description |
|---|---|---|---|
| client_name | string | – | Optional client or harness name and version. |
| kind | string | yes | – |
| message | string | yes | Feedback, or a description of the error with expected/actual behavior and reproduction steps. No secrets or private data. |
| request_id | string | – | Optional Kourier request ID associated with the error. |
No output schema declared.
No examples provided.
How do I install the Kourier MCP server?
Kourier is a hosted endpoint at https://kourier.sh/mcp, 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 · kourier.sh
claude mcp add --transport http sh-kourier-info 'https://kourier.sh/mcp'
What is the Kourier MCP server?
Kourier is an MCP server listed in the public MCP registry as sh.kourier/info. Discover flat-rate DeepSeek plans, model limits, API-key instructions, and coding-client setup. This page covers its hosted endpoint (https://kourier.sh/mcp).
Is the Kourier MCP server safe to use?
Kourier scores 75 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 Kourier MCP server expose?
Kourier exposes 8 tools: create_checkout_link, get_onboarding_status, complete_onboarding, submit_feedback, get_pricing, and 3 more. Their descriptions and schemas cost roughly 534 tokens of context every time the server is loaded.
Does the Kourier MCP server require authentication?
No. We connected to Kourier without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Kourier MCP server still maintained?
Kourier is still listed as active in the MCP registry. We last reached this channel on 19 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.