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/context-dot-dev/cursor-pluginWrote 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/context-dot-dev/cursor-plugin/prefer-context-dev-mcp)<a href="https://agentmods.dev/rules/context-dot-dev/cursor-plugin/prefer-context-dev-mcp"><img src="https://agentmods.dev/badge/rules/context-dot-dev/cursor-plugin/prefer-context-dev-mcp/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/context-dot-dev/cursor-plugin/prefer-context-dev-mcp"><img src="https://agentmods.dev/badge/rules/context-dot-dev/cursor-plugin/prefer-context-dev-mcp.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 | $0.00029 | $0.00429 |
| Opus 5.5 | $0.00012 | $0.00172 |
| Sonnet 5.5 | $0.00006 | $0.00086 |
| Haiku 4.5 | $0.00003 | $0.00043 |
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 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
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 - News about one company by name, domain, ticker, or ISIN:
get-news-search - One known page:
web-scrape; set only the neededformatsfields - Several linked pages:
web-crawl; URL inventory:web-map - Typed fields from a known page:
web-scrapewithformats: { json: true }andjsonParams.schema - Sourced JSON research when the URL is unknown:
web-answers - A local file:
parse-document - Visual brand profile by domain:
get-brand; raw or non-domain brand lookup:brand-retrieve-unified - Design system and fonts:
web-styleguide; rendered page:web-scrapewithformats: { screenshot: true } - Large asynchronous work:
submit-batch, thenget-batchandget-batch-results - Recurring change detection: the monitor tools
- Current credit balance and next refill:
get-usage; usage over time:get-usage-history
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.
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 Changed · +1 lines · +3 tokens per session 9ed648fc1d67
- 20d ago Changed · +1 lines · +3 tokens per session ccfcef24055d
- 1mo ago First seen · 26 lines · 23 tokens per session scan A 799fcf793965
prefer-context-dev-mcp is a cursor rule published in the GitHub repository context-dot-dev/cursor-plugin (10 stars, last pushed 13d ago), licensed MIT. It adds 29 tokens to every session and 429 once invoked, about $0.0001 per session on Opus 5.5. 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
vasu-playwright-utils
../../templates/cursor-rules/vasu-playwright-utils.mdc.
chrome-extension-manifest-rules
Specific rules related to the Chrome extension manifest file, ensuring proper structure and content.
vla-registry
Multi-model GUI/VL registry — browser wllama grounding (ShowUI-2B is default + E2E gate).
safari
This file, safari.mdc, serves as a repository for detailed working notes, observations, and learnings acquired during the process of automating Safari interactions, particularly for the MCP Inspector UI. It's intended to capture the nuances of trial-and-error, debugging steps, and insights into what worked, what…
scrapy
Cursor rule "scrapy" from Solihatun1/AI-Cursor-Scraping-Assistant, covering scrapy best practices, 1. code organization and structure, 1.1. directory structure, 1.2. file naming conventions and 1.3. module organization.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.