Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/noveldig/mcp-xhs-publisherWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/noveldig/mcp-xhs-publisher/mcp-advanced-concepts)<a href="https://agentmods.dev/rules/noveldig/mcp-xhs-publisher/mcp-advanced-concepts"><img src="https://agentmods.dev/badge/rules/noveldig/mcp-xhs-publisher/mcp-advanced-concepts/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/noveldig/mcp-xhs-publisher/mcp-advanced-concepts"><img src="https://agentmods.dev/badge/rules/noveldig/mcp-xhs-publisher/mcp-advanced-concepts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01201 | $0.01201 |
| Opus 5 | $0.00600 | $0.00600 |
| Sonnet 5 | $0.00240 | $0.00240 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade A, and why
mcp-advanced-concepts scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP 高级概念指南 (MCP Advanced Concepts Guide)
本指南涵盖了 MCP (Model Context Protocol) 中的一些高级概念,包括 Prompts(提示)、Sampling(采样)、Roots(根)和 Transports(传输)。理解这些概念有助于构建更复杂和功能更丰富的 MCP 服务器和客户端应用。
1. Prompts (提示)
- 定义: Prompts 在 MCP 中允许服务器向 LLM 提供可重用的提示模板和工作流。这有助于标准化与 LLM 的交互,并简化复杂任务的构建。
- 用途: 服务器可以暴露预定义的 prompt 模板,客户端(或 LLM)可以选择并填充这些模板以生成具体的请求。
- 组件:
- 模板 (Template): 包含占位符的文本,LLM 可以填充这些占位符。
- 参数 (Parameters): 定义模板中占位符的输入。
- 元数据 (Metadata): 描述提示的用途、预期输出等。
- 规则:
- 当服务器提供需要复杂或结构化输入的 LLM 交互时,应考虑使用 Prompts。
- Prompts 的设计应易于 LLM 理解和使用。
- 服务器应通过
listPrompts(如果 MCP 规范支持) 或类似机制暴露可用的 Prompts。
2. Sampling (采样)
- 定义: Sampling 允许 MCP 服务器向 LLM 请求文本补全 (completions),并对生成过程施加一定的控制(例如,温度、最大 token 数等采样参数)。
- 用途: 当服务器需要 LLM 生成文本(例如,根据上下文回答问题、总结信息或创作内容)时,可以使用 Sampling 功能。
- 机制: 服务器可以向其连接的客户端(通常是 LLM 服务代理)发送补全请求,并指定采样参数。
- 规则:
- 服务器应仅在确实需要 LLM 生成能力时才请求采样。
- 采样参数的选择应根据具体任务的需求进行调整。
- 对于
coze-mcp-server,虽然其主要作为工具和资源的提供者,但在某些工具的实现中(如chat_with_bot),可能间接涉及到代表用户向 Coze 后端(包含 LLM)发起类似"采样"的请求。
3. Roots (根)
- 定义: Roots 是 MCP 中用于组织和发现资源的顶层入口点。它们帮助客户端了解服务器提供了哪些主要的资源类别或功能区域。
- 用途: 客户端可以通过查询服务器的 Roots 来开始浏览可用的资源和服务。
- 结构: Roots 通常是一个层级结构,允许逻辑上对资源进行分组。
- 规则:
- 服务器应定义有意义的 Roots,以便客户端能够有效地导航其提供的资源。例如,
coze-mcp-server可能有bots和workspaces等 Roots。 - Roots 的设计应保持稳定,避免频繁更改导致客户端混淆。
- 服务器应定义有意义的 Roots,以便客户端能够有效地导航其提供的资源。例如,
4. Transports (传输)
- 定义: Transports 规定了 MCP 客户端和服务器之间如何交换消息。它定义了通信的底层机制。
- 标准: MCP 通常基于标准传输协议(如 WebSockets, STOMP over WebSockets, 或简单的 HTTP)进行通信,消息内容采用 JSON 格式。
- Python SDK: 在使用 modelcontextprotocol/python-sdk 时,开发者通常不需要直接处理底层的 Transport 细节,因为 SDK 会封装这些复杂性。
- 规则:
- 服务器实现应确保其 Transport 层与 MCP 规范兼容。
- 对于
coze-mcp-server,其通过uvx coze-mcp-server或python -m coze_mcp_server启动,并监听传入的 MCP 连接,其 Transport 机制由其依赖的 MCP 库(可能是 Python SDK)处理。 - 配置(如端口、协议)应清晰并在
[README.md](mdc:README.md)中说明,coze-mcp-server的 README 提供了在 Claude.app 和 Zed 中的配置示例,这些配置间接指定了如何连接到服务器的 Transport。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 61 lines · 1,201 tokens per session scan A 784694265ba3
mcp-advanced-concepts is a cursor rule published in the GitHub repository noveldig/mcp-xhs-publisher (1 stars, last pushed 1y ago), licensed MIT. It adds 1,201 tokens to every session, about $0.0060 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other cursor rules, from other repositories
baml
A set of rules for setting up BAML and help with syntax guidance.
co-dialectic
Co-Dialectic prompt sharpening and verification rules for Cursor.
prompt-routing
Route tasks to the correct Universal AI Engineering Prompt.
prompting-for-qe
Soạn/tinh chỉnh prompt cho tác vụ QE (sinh test case, phân tích requirement, tóm tắt tài liệu test, phân tích log) — đặc biệt khi output AI lan man, chung chung, bịa, hoặc muốn chốt prompt thành template tái dùng.
llm-zod-jsonschema
Best Practice for LLM Output Parsing with Zod and JSON Schema.
prompt-evals
Prompt eval fixtures — case design, assertions, versioning, CI gates, no PII in golden data.