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-resources)<a href="https://agentmods.dev/rules/noveldig/mcp-xhs-publisher/mcp-resources"><img src="https://agentmods.dev/badge/rules/noveldig/mcp-xhs-publisher/mcp-resources/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-resources"><img src="https://agentmods.dev/badge/rules/noveldig/mcp-xhs-publisher/mcp-resources.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 | $0.00889 | $0.00889 |
| Opus 5 | $0.00445 | $0.00445 |
| Sonnet 5 | $0.00178 | $0.00178 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
mcp-resources 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 12d 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.
What it actually says
MCP 资源指南 (MCP Resources Guide)
本指南详细说明了如何在 MCP (Model Context Protocol) 服务器(如 coze-mcp-server)中定义、暴露和管理资源。资源是 MCP 的核心概念之一,代表了服务器可以提供给 LLM 使用的数据和内容。
1. 资源定义
- 唯一标识 (URI): 每个资源都必须有一个唯一的 URI (Uniform Resource Identifier)。这个 URI 用于在 MCP 网络中寻址和引用资源。
- URI 格式通常为
mcp://<server_name>/<resource_type>/<resource_id>。 <server_name>应与服务器注册的名称一致。<resource_type>和<resource_id>应清晰地描述资源的类型和具体实例。
- URI 格式通常为
- 内容 (Content): 资源的主要部分是其内容,可以是文本、代码、JSON 数据等。内容应结构化且易于 LLM 理解和处理。
- 元数据 (Metadata): 资源可以包含元数据,提供关于内容的附加信息,如创建日期、作者、MIME 类型等。
- 权限 (Permissions): 服务器应能控制对资源的访问权限,确保只有授权的客户端可以读取或修改资源。
2. 资源暴露
- 列举资源 (
listResources): 服务器必须实现listResources方法,允许客户端发现可用的资源。可以支持过滤和分页。 - 订阅资源 (
subscribeToResource): 对于可能随时间变化的资源,服务器应支持客户端通过subscribeToResource订阅资源更新。当资源发生变化时,服务器会向订阅的客户端发送resourceChanged通知。 - 检索资源 (
retrieveResource): 客户端可以通过retrieveResource请求特定 URI 的资源内容和元数据。
3. coze-mcp-server 中的资源示例
coze-mcp-server 暴露了与 Coze 平台相关的资源,例如:
- 工作空间 (Workspaces): 可能的资源类型如
mcp://coze-mcp-server/workspaces/<workspace_id>。 - 机器人 (Bots): 可能的资源类型如
mcp://coze-mcp-server/bots/<bot_id>。
服务器应清晰地在其文档(如 [README.md](mdc:README.md))中说明其提供的资源类型及其 URI 结构。
4. 设计原则
- 粒度 (Granularity): 合理设计资源的粒度。过于粗粒度的资源可能包含过多不相关信息,而过于细粒度的资源可能导致过多的请求和管理复杂性。
- 原子性 (Atomicity): 资源的更新应尽可能原子化,以避免不一致的状态。
- 幂等性 (Idempotency): 资源操作(如创建、更新)应设计为幂等的,多次执行同一操作应产生相同的结果。
- 版本控制 (Versioning): 对于重要的或经常变化的资源,考虑支持版本控制。
5. 实现说明
- 使用 MCP SDK (如 modelcontextprotocol/python-sdk) 提供的工具和类型来定义和处理资源。
- 资源内容应针对 LLM 进行优化,使其易于解析和利用。
- 确保资源 URI 的稳定性和唯一性。
- 关于如何在项目中组织资源实现代码,可以参考 项目结构指南 中关于
resources/子包的建议。
通过良好设计的资源,MCP 服务器可以有效地向 LLM 提供上下文信息,增强其执行任务的能力。
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.
- 12d ago First seen · 51 lines · 889 tokens per session scan A 99e7b003b647
mcp-resources is a cursor rule published in the GitHub repository noveldig/mcp-xhs-publisher (1 stars, last pushed 1y ago), licensed MIT. It adds 889 tokens to every session, about $0.0044 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
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.