Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/rules/rushi053/privacypage-mcp/hq)<a href="https://agentmods.dev/rules/rushi053/privacypage-mcp/hq"><img src="https://agentmods.dev/badge/rules/rushi053/privacypage-mcp/hq/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/rushi053/privacypage-mcp/hq"><img src="https://agentmods.dev/badge/rules/rushi053/privacypage-mcp/hq.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 | $0.00396 | $0.00396 |
| Opus 5 | $0.00198 | $0.00198 |
| Sonnet 5 | $0.00079 | $0.00079 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
hq 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 4d 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
privacypage-mcp (distribution for Stream B)
Business context and protocols: /Users/rushiraj/Desktop/hq/ — read CONTEXT.md, LOG.md, BACKLOG.md, PLAYBOOK.md first.
Facts
- TypeScript MCP server exposing 6 PrivacyPage tools to AI agents. Talks to https://privacypage.io APIs; users supply a
privacypage_license_key. - Published to: npm
privacypage-mcp(2FA on publish — Rushiraj runsnpm publish), official MCP Registry asio.github.rushi053/privacypage-mcp(server.json; description must stay ≤100 chars), Glama (claimed), Smithery asrjadeja053/privacypage-mcpvia MCPB bundle. - Smithery quirks: needs a
manifest.json(MCPB 0.3) with full JSON-SchemainputSchemaper tool; pack with plainzip, notmcpb pack(which strips the schemas). Steps inPUBLISH.md.*.mcpbis gitignored. README.mdhas a "Data handling" section — keep it accurate if payloads or storage change.
Conventions
- A release touches: version in
package.json+server.json+manifest.json(keep in sync), changelog/README, npm publish (Rushiraj),mcp-publisher publish, Smithery re-pack + resubmit. - If PrivacyPage API behavior changes (e.g. preview semantics), update tool descriptions here the same day.
- Never read
.env*.
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.
- 4d ago First seen · 20 lines · 396 tokens per session scan A 986a3faf0faf
hq is a cursor rule published in the GitHub repository rushi053/privacypage-mcp (0 stars, last pushed 6d ago), licensed MIT. It adds 396 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 2026-09-04.
Other cursor rules, from other repositories
903-story-template
ALWAYS use when creating or updating story files to ensure proper tracking and implementation. This rule enforces consistent story structure with tasks, context, and progress tracking.
state-memory-mcp
This project tracks workflow state, tasks, design decisions, and blockers using state-memory-mcp with project slug "state-memory-mcp".
cursor_conductor_task_management
description: Best practices for effective task management with Conductor Tasks in an AI-assisted workflow globs: / alwaysApply: true.
awp-auto
When the user says awp auto, awp auto strict, or runs the Kanban Auto command — enforce the per-task loop (not batch delivery).
task-status-update-rule
Always When updating the status of a task.
task-tracking-basic
Basic task tracking for Level 2 Simple Enhancement tasks.