project-structure

project-structure is a cursor rule for Cursor from SecretRichGarden/metasota-API-MCP. It costs 408 tokens per session, scanned A, original, Apache-2.0.

A project-structure guide for a Node.js and TypeScript MCP server that connects to the Metaso Search API. Node.js runs the server, TypeScript defines its source code, and MCP lets AI assistants call its tools.

In plain words
What is it for?
Use it to find the entry point, understand the build and module setup, configure the API key and endpoint, and navigate the repository.
Why use it?
It shows where source, compiled files, documentation, configuration, and dependencies belong, reducing guesswork when changing the project.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions Cursor.

Good fit Use it to find the entry point, understand the build and module setup, configure the API key and endpoint, and navigate the repository.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/secretrichgarden/metasota-api-mcp/project-structure
Install

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.

Clone the repo
git clone --depth 1 https://github.com/SecretRichGarden/metasota-API-MCP

Made for: Cursor.

Wrote 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.

agentmods badge for project-structure

README.md
[![agentmods](https://agentmods.dev/badge/rules/secretrichgarden/metasota-api-mcp/project-structure.svg)](https://agentmods.dev/rules/secretrichgarden/metasota-api-mcp/project-structure)
Your own site
<a href="https://agentmods.dev/rules/secretrichgarden/metasota-api-mcp/project-structure"><img src="https://agentmods.dev/badge/rules/secretrichgarden/metasota-api-mcp/project-structure.svg" alt="Measured on agentmods" height="20"></a>
Per session 408 This file is loaded in full into every session.
When invoked 408 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00408 $0.00408
Opus 5 $0.00204 $0.00204
Sonnet 5 $0.00082 $0.00082
Haiku 4.5 $0.00041 $0.00041

Measured 7d ago against content hash 65466b16009b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

project-structure 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 7d 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.

.cursor/rules/project-structure.mdc · 44 lines

What it actually says

Metaso Search MCP Project Structure

This is a Node.js/TypeScript project implementing a Model Context Protocol (MCP) server for Metaso Search API integration.

Project Overview

  • Type: MCP Server (stdio transport)
  • Language: TypeScript (ES2022, Node16 modules)
  • Main Entry: src/index.ts (compiled to dist/index.js)
  • Package Manager: npm
  • Key Dependencies:
    • @modelcontextprotocol/sdk - MCP protocol implementation
    • axios - HTTP client for API calls
    • zod - Schema validation

Project Structure

metasota_API_MCP/
├── src/                    # TypeScript source files
│   └── index.ts           # Main MCP server entry point
├── dist/                   # Compiled JavaScript (generated)
├── docs/                   # Documentation
│   ├── # 秘塔搜索MCP工具开发完整方案.md
│   └── 秘塔搜索API所有功能整理.md
├── .cursor/rules/          # Cursor rules
├── package.json            # Project configuration
└── tsconfig.json          # TypeScript configuration

Key Configuration

  • API Endpoint: https://metaso.cn/api/v1
  • Authentication: Bearer token via METASO_API_KEY environment variable
  • Transport: stdio (for MCP communication)
  • Module System: ES Modules ("type": "module")

Development Workflow

  1. Source code in src/ directory
  2. TypeScript compiles to dist/ directory
  3. Use npm run build to compile
  4. Use npm start to run compiled code
  5. Binary entry point: dist/index.js (via bin in package.json)
Changes

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.

  1. 7d ago First seen · 44 lines · 408 tokens per session scan A 65466b16009b

Subscribe to this mod's changes

project-structure is a cursor rule published in the GitHub repository SecretRichGarden/metasota-API-MCP (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 408 tokens to every session, about $0.0020 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.