agentmods.dev

prefer-context-dev-mcp

Rules for choosing Context.dev tools for web search, page scraping, structured extraction, brand data, monitoring, and batch jobs.

In plain words
What is it for?
Use them when working with public websites or Context.dev features such as crawling pages, extracting fields, checking brands, or managing recurring monitors.
Why use it?
They reduce tool-selection mistakes and make clear when an operation may change account data or trigger an outside action.

Cursor rule

4 14d ago A scan 23 tokens original MIT
View the source file context-dot-dev/cursor-plugin
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.

agentmods
npx agentmods add rules/context-dot-dev/cursor-plugin/prefer-context-dev-mcp
Clone the repo
git clone --depth 1 https://github.com/context-dot-dev/cursor-plugin
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 364 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00023 $0.00364
Opus 5 $0.00012 $0.00182
Sonnet 5 $0.00005 $0.00073
Haiku 4.5 $0.00002 $0.00036

Measured yesterday against content hash 799fcf793965, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prefer-context-dev-mcp 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 yesterday.

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.

rules/prefer-context-dev-mcp.mdc · 26 lines

What it actually says

Use the context MCP server instead of memory when the user needs current public-web or Context.dev data.

Choose the narrowest direct tool:

  • Unknown source or current topic: web-search
  • One known page: web-scrape-markdown; raw DOM only: web-scrape-html
  • Several linked pages: web-crawl; URL inventory: web-scrape-sitemap
  • Typed fields from a site: web-extract
  • A local file: parse-document
  • Visual brand profile by domain: get-brand; raw or non-domain brand lookup: brand-retrieve-unified
  • Design system, fonts, or rendered page: web-styleguide, web-fonts, or web-screenshot
  • Industry classification: web-naics or web-sic
  • Large asynchronous work: submit-batch, then get-batch and get-batch-results
  • Recurring change detection: the monitor tools

Do not claim that MCP exposes endpoints absent from its tool list. Prefer bare domains where a tool asks for a domain and full https:// URLs where a tool asks for a URL. Preserve source URLs and distinguish sourced facts from inference.

Creating, updating, running, cancelling, or deleting monitors and batches changes account state. Perform those actions only when the user clearly requests them, and obtain confirmation before destructive operations.

If the MCP server is unavailable or returns 401, tell the user to enable context in Cursor Settings → Tools & MCP and complete OAuth. Do not ask the user to paste an API key into chat.

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. yesterday First seen · 26 lines · 23 tokens per session scan A 799fcf793965

Subscribe to this mod's changes

prefer-context-dev-mcp is a cursor rule published in the GitHub repository context-dot-dev/cursor-plugin (4 stars, last pushed 14d ago), licensed MIT. It adds 23 tokens to every session and 364 once invoked, about $0.0001 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.

Browser automationResearch
Related

Other cursor rules, from other repositories

webkit-browser

Cursor rule "webkit-browser" from duckduckgo/apple-browsers, covering webkit & browser development guidelines, webview configuration, basic webview setup, user scripts management and tab management.

duckduckgo/apple-browsers · 0 tokens

cypress-e2e-testing-cursorrules-prompt-file

Cursor rules for Cypress development with E2E testing.

XD3an/awesome-ai-coding-all-in-one · 709 tokens

vasu-playwright-utils

../../templates/cursor-rules/vasu-playwright-utils.mdc.

vasu31dev/playwright-ts-lib · 14 tokens

dev-browser

Fallback browser automation with persistent Chrome state. Use only when Browser Use is unavailable or blocked.

udecode/plate-template · 18 tokens

node-dependencies

Enforce Node.js versioning and package management best practices.

abderrahimghazali/cursor-rules · 0 tokens

security-standards

Cursor rule "security-standards" from wjgogogo/cursor-rules, covering 安全规范, 核心原则 [p0], 输入验证, xss 防护 and csrf 防护.

wjgogogo/cursor-rules · 0 tokens