GitHub
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
作者提供的说明(英文原文)
Discover flat-rate DeepSeek plans, model limits, API-key instructions, and coding-client setup.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
适用于网页版、桌面版和手机版 Claude:
https://kourier.sh/mcp在终端中运行这条命令
claude mcp add --transport http info https://kourier.sh/mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"info": {
"url": "https://kourier.sh/mcp"
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"info": {
"type": "http",
"url": "https://kourier.sh/mcp"
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
ChatGPT 只能连接互联网上的服务器:
https://kourier.sh/mcp菜单名称可能因套餐和版本不同而略有差异。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月8日
注册名称已通过域名 kourier.sh 验证(注册中心会核实域名所有权)
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
尚未检查;我们会轮流检查各个端点
尚未检查;我们会轮流检查各个端点
尚未检查;我们会在检查端点时读取工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于–,最新版本(1.0.0)于28天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
同一分类中有:GitHub, Desktop Commander, Cloudflare MCP
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
MCP server for terminal commands, file operations, and process management
Cloudflare MCP servers
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Remote Model Context Protocol (MCP) server for Kourier — flat-rate hosted AI inference for coding agents.
Use the MCP server to discover plans, check model limits, configure your coding client, start human-approved subscription onboarding, and submit account-attributed feedback or error reports. Kourier serves DeepSeek V4.1 Flash through OpenAI-compatible and Anthropic-compatible inference APIs, with no per-token billing or request-volume quotas. Plans differ by concurrency.
https://kourier.sh/mcp
Transport: Streamable HTTP, stateless, JSON responses. Authentication: none required for information or onboarding; submit_feedback requires a Kourier API key in the connection's Authorization: Bearer header.
MCP provides service information and setup instructions, not model inference. Inference uses a subscription API key at
https://api.kourier.sh/v1(OpenAI-compatible) orhttps://api.kourier.sh/anthropic(Anthropic-compatible).
This repository documents the hosted service; there is no local server to install or run. The live MCP server provides eight tools: four read-only information tools, three onboarding tools, and one authenticated feedback tool. Recurring billing and agent access require explicit human approval in the browser before a dedicated inference key can be issued.
claude mcp add --transport http kourier https://kourier.sh/mcp
mcpServersAdd this entry to your client's MCP configuration:
{
"mcpServers": { "kourier": { "url": "https://kourier.sh/mcp" } } }
Configuration formats vary by client; use the remote Streamable HTTP URL above where your client requests a server URL.
Once connected, ask: “What are Kourier's plans, and how do I configure my coding client to use it?”
Adding this MCP server does not change the model powering your coding client. Use get_setup_instructions to configure Kourier as the inference provider separately.
Connecting to MCP and using the information or onboarding tools requires no connection credentials. Onboarding status and completion require the private onboarding_token returned by create_checkout_link. Only submit_feedback requires an API-key bearer header. Keep tokens and keys out of logs, public messages, report content, and repositories.
| Tool | Arguments | What it does |
|---|---|---|
get_pricing | None | Returns public plans, monthly prices, concurrency limits, and usage-cap information. |
get_models | None | Returns the served model's exact API identifier and context/output limits. |
get_api_key_instructions | None | Explains dashboard signup, agent sign-in, and OAuth with PKCE. Does not return an API key itself. |
get_setup_instructions | Optional harness | Returns configuration guidance for oh-my-pi, claude-code, codex, or openai-compatible. Omit the argument for generic OpenAI-compatible settings. |
create_checkout_link | plan, client_name; optional harness | Starts verified sign-in, recurring Starter/Pro purchase, and explicit agent-access approval. Returns a browser link and approval code; creating the link does not itself charge or issue a key. |
get_onboarding_status | Private onboarding_token | Checks approval and entitlement status. Poll every five seconds; complete only when ready, and stop on issued, denied, or expired. |
complete_onboarding | Private onboarding_token | Exchanges ready onboarding for a dedicated revocable inference key once. Save it securely; never retry after issuance or ambiguous delivery—check status instead. |
submit_feedback | kind, message; optional request_id, client_name | Saves account-attributed feedback or an error report. Requires a Kourier API key in the connection's Authorization: Bearer header, never in tool arguments. |
For example, call get_setup_instructions with:
{
"harness": "claude-code" }
The server also exposes the `kourier-setup` Markdown resource and the `configure_kourier` prompt, which accepts the same optional harness value.
Use `submit_feedback` to send product feedback or report a Kourier error. Reports are attributed to the account that owns the API key.
Authorization: Bearer . Store the key in your client's private credential settings; never add a real key to repository configuration.| Argument | Required | Value |
|---|---|---|
kind | Yes | feedback for product feedback, or error for an error report. |
message | Yes | Nonblank text, 1–8,000 characters after trimming. For errors, describe expected behavior, actual behavior, and reproduction steps without private data. |
request_id | No | A Kourier request ID associated with the error, 1–200 characters after trimming. |
client_name | No | Client or harness name and version, 1–80 characters after trimming. |
NUL bytes, blank supplied strings, extra fields, and credential arguments are not accepted.
The following command saves a feedback report when run with a valid key. Replace the sample message with feedback the user has approved, and set KOURIER_API_KEY privately in your environment before running it:
curl https://kourier.sh/mcp \
-H "Content-Type: application/json" \ -H "Accept: application/json, text/event-stream" \ -H "Authorization: Bearer $KOURIER_API_KEY" \ --data '{ "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "submit_feedback", "arguments": { "kind": "feedback", "message": "Please add more coding-client setup examples to the documentation.", "client_name": "curl" } } }'
Successful submissions return a receipt with id and created_at in result.structuredContent; the same receipt is included as JSON text in result.content. Tool failures set result.isError to true and return error and error_description.
retry_after before submitting again.| Plan | Monthly price (USD) | Concurrent requests |
|---|---|---|
| Starter | $20 | 1 |
| Pro | $50 | 3 |
Neither public plan has a five-hour, weekly, or monthly request or token quota. A concurrency slot becomes available when its request finishes. “No usage quotas” does not mean unlimited simultaneous requests.
Consult get_pricing or the pricing page for current terms; the MCP endpoint accepts JSON-RPC POST requests, not ordinary browser GET requests.
| Setting | Value |
|---|---|
| Model | DeepSeek V4.1 Flash |
| Exact API model identifier | deepseek-v4.1-flash |
| OpenAI-compatible base URL | https://api.kourier.sh/v1 |
| Anthropic-compatible base URL | https://api.kourier.sh/anthropic |
| Maximum combined prompt + output context | 262,144 tokens (256K) |
| Maximum output per response | 16,384 tokens |
| Authentication | Authorization: Bearer ; the Anthropic surface also accepts x-api-key |
Use the exact model identifier; aliases are not supported. Check get_models and the model documentation for current availability and limits.
get_setup_instructions for your client and apply the returned settings.For agent-assisted sign-in, follow Kourier's auth.md and the agent sign-in guide. Human approval happens in the browser; connecting to the public MCP server alone does not authorize billing or grant inference access.
Keep API keys in environment variables or your client's private credential store. Never commit them to a repository or paste them into public issues. The public information tools do not need your inference key.
With an active subscription and KOURIER_API_KEY set in your environment:
curl https://api.kourier.sh/v1/chat/completions \
-H "Authorization: Bearer $KOURIER_API_KEY" \ -H "Content-Type: application/json" \ --data '{ "model": "deepseek-v4.1-flash", "messages": [{"role": "user", "content": "Explain what this coding API supports."}], "max_tokens": 256 }'
Send an initialization request without an API key:
curl https://kourier.sh/mcp \
-H "Content-Type: application/json" \ -H "Accept: application/json, text/event-stream" \ --data '{ "jsonrpc": "2.0", "id": 1, "method": "initialize", "params": { "protocolVersion": "2025-11-25", "capabilities": {}, "clientInfo": {"name": "kourier-quickstart", "version": "1.0.0"} } }'
The response identifies the server as kourier-info and advertises tools, resources, and prompts. Supported protocol versions are 2025-11-25, 2025-06-18, and 2025-03-26.
List the available tools:
curl https://kourier.sh/mcp \
-H "Content-Type: application/json" \ -H "Accept: application/json, text/event-stream" \ --data '{"jsonrpc":"2.0","id":2,"method":"tools/list","params":{}}'
The endpoint does not offer a persistent SSE stream or MCP sessions. GET and DELETE return 405; use JSON-RPC POST. Normal MCP clients handle protocol initialization automatically.
The hosted service is published in the official MCP Registry as `sh.kourier/info`. The repository includes server.json for registry metadata, glama.json for maintainer verification, and lhm.plugin.json for LobeHub publication. Directory account verification and review are separate from registry publication.
For documentation correction
只显示了开头部分;其余内容请在仓库中阅读