Kourier MCP server
sh.kourier/infokourier.shstreamable-httpv1.0.0Scanned
Discover flat-rate DeepSeek plans, model limits, API-key instructions, and coding-client setup.
8 tools: 2 do something that can't be undone, 1 change things and 5 only read.
- Reads private data · 1
- Reads text others write · 3
- Can send data out · 1
- No findings
Tools listed without sign-in. Remote posture
Anlyon alternative
3 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →Its sign-in does not let Anlyon set up an OAuth client on its own, so there is no link to it here.
What the Kourier MCP server can do
The Kourier MCP server is published by kourier.sh, a domain the MCP Registry verified. It has 8 tools. It can do things that cannot be undone, such as sending, paying or publishing (complete_onboarding and submit_feedback) and create or change data (1 tool: create_checkout_link), but cannot delete data. 5 tools only read.
1 tool reads private data (get_onboarding_status); 3 tools bring in text other people can write (create_checkout_link, get_onboarding_status and complete_onboarding); 1 tool can send data out of your system (complete_onboarding). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 18, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
8 tools
Can't be undone 2Claude Code: ask
complete_onboardingDeliver a dedicated revocable inference key exactly once after human approval and active entitlement.Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "deliver": a word for sending, and what is sent cannot be taken back.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe description's first verb is "deliver": it sends or publishes something to other people.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
submit_feedbackSend feedback or report a Kourier error, attributed to your account.No findings
Why it is in this group
- The name "submit_feedback" says "submit": a word for a change.
- The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
Changes things 1Claude Code: ask
create_checkout_linkCreate a verified sign-in, recurring Starter/Pro plan and explicit agent access approval link.Reads text others writeNo findings
Why it is in this group
- The name "create_checkout_link" says "create": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Only reads 5Show 5 read-only tools
get_api_key_instructionsHow a person or an agent obtains a Kourier API key: dashboard sign-up, agent sign-in (auth.md), or OAuth with PKCE.No findings
Why it is in this group
- The name "get_api_key_instructions" says "get": a word for reading.
Description, as the server wrote it How a person or an agent obtains a Kourier API key: dashboard sign-up, agent sign-in (auth.md), or OAuth with PKCE.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_modelsThe model Kourier serves, its API model string, and context limits.No findings
Why it is in this group
- The name "get_models" says "get": a word for reading.
Description, as the server wrote it The model Kourier serves, its API model string, and context limits.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_onboarding_statusCheck approval and signed-webhook-backed entitlement, without identity or secrets.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_onboarding_status" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "secret": it reads secrets.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_pricingKourier's plans, monthly prices, concurrency limits, and what has no usage cap.No findings
Why it is in this group
- The name "get_pricing" says "get": a word for reading.
Description, as the server wrote it Kourier's plans, monthly prices, concurrency limits, and what has no usage cap.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_setup_instructionsConfiguration for using Kourier from Oh My Pi, Claude Code, Codex CLI, or any OpenAI-compatible client.No findings
Why it is in this group
- The name "get_setup_instructions" says "get": a word for reading.
Description, as the server wrote it Configuration for using Kourier from Oh My Pi, Claude Code, Codex CLI, or any OpenAI-compatible client.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
3 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write3
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__info__complete_onboarding"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:18 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 3
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://kourier.sh/.well-known/oauth-protected-resource
- Authorization servers
- https://app.kourier.sh
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- no
- Client ID metadata documents
- no
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (2 irreversible, 1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://kourier.sh/mcp: tools/list returned 8 tools to an anonymous client, including complete_onboarding (irreversible), submit_feedback (irreversible), create_checkout_link (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http info https://kourier.sh/mcpclaude mcp add --transport http info https://kourier.sh/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__info__get_onboarding_status",
"mcp__info__get_pricing",
"mcp__info__get_setup_instructions",
"mcp__info__get_api_key_instructions",
"mcp__info__get_models"
],
"ask": [
"mcp__info__create_checkout_link",
"mcp__info__complete_onboarding",
"mcp__info__submit_feedback"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as info. Review it before you use it.
Capability tags behind 3 rules
- mcp__info__create_checkout_link untrusted-input
- mcp__info__get_onboarding_status private-data, untrusted-input
- mcp__info__complete_onboarding untrusted-input, outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/sh.kourier/info/verify?hash=a1adf8e903447c4e46ffe5ea872ca1008b74bab546c81dba2161f9ba1e4c3d6f" | jq -e '.changed == false'Pinned hash a1adf8e90344, from Nov 18, 2026, 07:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/sh.kourier/info/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/sh.kourier/info)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:54 UTC.
Kourier MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Kourier MCP server safe?
- No scan can promise that. What its definitions show: 8 tools, 3 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Kourier MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Kourier MCP server do things that cannot be undone?
- Yes. 2 tools can send, pay, publish or merge: complete_onboarding and submit_feedback.
What tools does the Kourier MCP server have?
- 8 tools: 2 irreversible, 1 write, 5 read. complete_onboarding, submit_feedback, create_checkout_link, get_onboarding_status, get_pricing, get_setup_instructions, get_api_key_instructions and get_models.
Does the Kourier MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Kourier MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): complete_onboarding.
Has the Kourier MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 18, 2026.