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-tools)<a href="https://agentmods.dev/rules/noveldig/mcp-xhs-publisher/mcp-tools"><img src="https://agentmods.dev/badge/rules/noveldig/mcp-xhs-publisher/mcp-tools/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-tools"><img src="https://agentmods.dev/badge/rules/noveldig/mcp-xhs-publisher/mcp-tools.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 | $0.01014 | $0.01014 |
| Opus 5 | $0.00507 | $0.00507 |
| Sonnet 5 | $0.00203 | $0.00203 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
mcp-tools 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 10d 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 工具指南 (MCP Tools Guide)
本指南阐述了在 MCP (Model Context Protocol) 服务器(例如 coze-mcp-server 作为一种可能的实现)中如何定义、实现和暴露工具。工具使 LLM 能够通过服务器执行操作和与外部系统交互。
参考:
- MCP Tools Concepts
coze-mcp-server的[README.md](mdc:README.md)(可作为查看具体工具列表的示例)
1. 工具定义
- 名称 (Name): 每个工具必须有一个唯一的名称,用于客户端引用。名称应清晰描述工具的功能,例如
create_bot。 - 描述 (Description): 提供工具功能的详细描述,LLM 会使用此描述来理解工具的用途和何时使用它。
- 参数 (Parameters): 定义工具执行所需的输入参数。每个参数应有:
- 名称 (Name)
- 类型 (Type): 如 string, number, boolean, array, object。
- 描述 (Description): 清晰说明参数的含义和用途。
- 是否必需 (Required): 指示参数是否为必需。
- 返回类型 (Return Type): (可选) 描述工具执行成功后返回的数据结构和类型。这有助于 LLM 理解工具的输出。
2. 工具暴露与执行
- 列举工具 (
listTools): 服务器必须实现listTools方法,允许客户端发现服务器提供的所有可用工具及其定义。 - 执行工具 (
executeTool): 当客户端(通常代表 LLM)决定使用某个工具时,它会发送executeTool请求,包含工具名称和所需的参数。服务器负责执行该工具的逻辑并返回结果。
3. coze-mcp-server 中的工具示例
以下列出 coze-mcp-server (作为一个具体例子) 提供的一些工具,以帮助理解工具的多样性:
list_workspaces: 获取工作空间列表。list_bots: 获取机器人列表。create_bot: 创建机器人。get_me: 获取当前用户信息。retrieve_bot: 检索机器人信息。update_bot: 更新机器人。publish_bot: 将机器人发布到 API 通道。chat_with_bot: 与机器人聊天。chat_with_workflow: 与工作流聊天。list_voices: 列出可用语音。
这些工具的具体实现方式和在项目中的组织,应遵循通用的项目结构指南中关于模块化和包架构的建议,例如将工具逻辑组织在专门的 tools/ 子包下。
4. 设计原则
- 原子性与单一职责: 工具应设计为执行单一、明确的操作。复杂的操作可以分解为多个更小的工具。
- 清晰的参数和描述: 参数和工具描述对于 LLM 能否正确有效地使用工具至关重要。描述应具体、无歧义,并提供足够上下文。
- 错误处理: 工具执行可能失败。服务器应能处理错误情况,并向客户端返回结构化的错误信息,帮助 LLM 理解失败原因。
- 幂等性: 尽可能将工具设计为幂等的。例如,重复调用
create_bot并使用相同的参数,如果机器人已存在,则应返回现有机器人的信息而不是创建重复项或报错(除非特定设计如此)。 - 安全性: 对于执行敏感操作或与外部系统交互的工具,必须实施严格的安全措施和权限检查。
5. 实现说明
- 使用 MCP SDK (如 modelcontextprotocol/python-sdk) 来简化工具的定义和消息处理。
- 工具的业务逻辑应与 MCP 协议处理代码分离,以保持代码整洁和可维护性。
- 详细记录每个工具的参数、行为和预期输出。
通过精心设计的工具,MCP 服务器可以极大地扩展 LLM 的能力,使其能够执行更广泛的任务并与真实世界系统交互。
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.
- 10d ago First seen · 61 lines · 1,014 tokens per session scan A f65adcb7a1b9
mcp-tools is a cursor rule published in the GitHub repository noveldig/mcp-xhs-publisher (1 stars, last pushed 1y ago), licensed MIT. It adds 1,014 tokens to every session, about $0.0051 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.