# Kourier

> Discover flat-rate DeepSeek plans, model limits, API-key instructions, and coding-client setup.

- name: sh.kourier/info
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 95/100
- quality: 91/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/sh.kourier%2Finfo
- tools: https://api.protogrid.dev/v1/servers/sh.kourier%2Finfo/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "info": {
      "type": "http",
      "url": "https://kourier.sh/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 99
- freshness: 100
- provenance: 85
- drivers: +repository +dns-namespace +website +reachable +uptime-97% +updated-10d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 91/100 (strong)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 8 of 8 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 1,082 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: 4 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 8, about 1,082 tokens to load them all
- tool set hash: 57a2409ecabb9412e0a51c00c2122da6
- tools last changed: 2026-10-15T10:08:52.467Z
- badge: [![protogrid quality](https://protogrid.dev/badge/sh.kourier/info.svg)](https://protogrid.dev/servers/sh.kourier/info)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-15 `submit_feedback` added
  - 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.
- 2026-10-11 `complete_onboarding` added
  - 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.
- 2026-10-11 `get_onboarding_status` added
  - 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.
- 2026-10-11 `create_checkout_link` added
  - 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.

Full history: https://api.protogrid.dev/v1/servers/sh.kourier%2Finfo/changes

## Remotes

- https://kourier.sh/mcp (streamable-http, auth none, reachable true, uptime30d 0.9736842)

## Packages

_none_

## Tools (8)

- `complete_onboarding`: 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.
- `create_checkout_link`: 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.
- `get_api_key_instructions`: How a person or an agent obtains a Kourier API key: dashboard sign-up, agent sign-in (auth.md), or OAuth with PKCE.
- `get_models`: The model Kourier serves, its API model string, and context limits.
- `get_onboarding_status`: 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.
- `get_pricing`: Kourier's plans, monthly prices, concurrency limits, and what has no usage cap.
- `get_setup_instructions`: Configuration for using Kourier from Oh My Pi, Claude Code, Codex CLI, or any OpenAI-compatible client.
- `submit_feedback`: 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.