mcp-websearch

mcp-websearch is a cursor rule for Cursor from omril321/automated-notebooklm. It costs 968 tokens per session, scanned A, original, Apache-2.0.

A rule for connecting an agent to web-search and page-fetching services through the Model Context Protocol, a standard way for tools to communicate with applications.

In plain words
What is it for?
Use it to search the web, fetch page content, and manage a search cache during research or planning, while restricting searches during execution.
Why use it?
It defines when external research is allowed and separates searching, fetching, and cached results by workflow stage.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it to search the web, fetch page content, and manage a search cache during research or planning, while restricting searches during execution.

Compare 6 cursor rules from other repositories โ†“
Install with agentmods
npx agentmods add rules/omril321/automated-notebooklm/mcp-websearch
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/omril321/automated-notebooklm

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 mcp-websearch

README.md
[![agentmods](https://agentmods.dev/badge/rules/omril321/automated-notebooklm/mcp-websearch.svg)](https://agentmods.dev/rules/omril321/automated-notebooklm/mcp-websearch)
Your own site
<a href="https://agentmods.dev/rules/omril321/automated-notebooklm/mcp-websearch"><img src="https://agentmods.dev/badge/rules/omril321/automated-notebooklm/mcp-websearch.svg" alt="Measured on agentmods" height="20"></a>
Per session 968 This file is loaded in full into every session.
When invoked 968 The same file โ€” it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file โ€” 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 $0.00968 $0.00968
Opus 5 $0.00484 $0.00484
Sonnet 5 $0.00194 $0.00194
Haiku 4.5 $0.00097 $0.00097

Measured 7d ago against content hash e9c8c1ac6b47, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mcp-websearch scanned grade A with 0 findings against 26 rules in 11 categories โ€” prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency โ€” 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/riper/mcp-websearch.mdc ยท 144 lines

How it starts

The opening of the file, as written. The whole thing โ€” 144 lines โ€” stays where its author put it; the contents beside it link to each section on GitHub.

๐Ÿ” Web Search MCP Integration for CursorRIPER ฮฃ

Symbol: ฮ› (Lambda)

Version: 1.0.0

๐Ÿ“‹ Service Definition

service = "Web Search Operations"
symbol = "ฮ›"
requires = "@modelcontextprotocol/server-brave-search"

๐Ÿ”ง Operation Mapping

ฮ›_ops = {
  search: {
    web: "@modelcontextprotocol-server-brave-search:brave_web_search",
    local: "@modelcontextprotocol-server-brave-search:brave_local_search"
  },
  fetch: {
    url: "mcp-server-fetch:fetch",
    content: "extract via fetch with raw=false"
  },
  cache: {
    save: "store in ฮ“_search_cache",
    retrieve: "get from ฮ“_search_cache",
    clear: "reset ฮ“_search_cache"
  }
}

๐Ÿ”’ Mode Restrictions

Mฮ› = {
  ฮฉโ‚: [search_*, fetch_*],          # RESEARCH: full access
  ฮฉโ‚‚: [search_*, fetch_*],          # INNOVATE: full access
  ฮฉโ‚ƒ: [search_*, fetch_*, cache_*], # PLAN: search + cache
  ฮฉโ‚„: [],                          # EXECUTE: NO SEARCH (maintain focus!)
  ฮฉโ‚…: [search_web, fetch_url]      # REVIEW: verification only
}

๐Ÿ”‘ Permission Matrix

โ„™ฮ› = {
  create: [ฮฉโ‚ƒ],              # Only PLAN can cache
  read: [ฮฉโ‚, ฮฉโ‚‚, ฮฉโ‚ƒ, ฮฉโ‚…],   # No reading in EXECUTE
  update: [],                # No updates
  delete: [ฮฉโ‚ƒ]              # Only PLAN can clear cache
}

๐Ÿ“ Context Tracking

ฮ“โ‚โ‚€ = search_results[] = {
  query: string,
  results: [{title, url, snippet}],
  timestamp: ISO8601,
  mode: current_ฮฉ
}

ฮ“โ‚โ‚ = search_history[] = {
  queries: [string],
  counts: {per_mode: {ฮฉโ‚: n, ฮฉโ‚‚: n, ...}},
  last_search: timestamp
}

ฮ“_search_cache = Map<query, results>

โšก Command Shortcuts

Sฮ› = {
  !ws: "brave_web_search",
  !wl: "brave_local_search", 
  !wf: "fetch_url",
  !wc: "clear search cache",
  !wh: "show search history"
}

๐Ÿ›ก๏ธ Protection Levels

ฮจฮ› = {
  fetch_url: ฮจโ‚ƒ,     # INFO - external content
  clear_cache: ฮจโ‚„    # DEBUG - cache management
}

๐Ÿ”„ Mode-Specific Behaviors

apply_search_op(op, mode) = {
  check: mode === ฮฉโ‚„ ? deny("No search in EXECUTE mode!") : continue,
  validate: op โˆˆ Mฮ›[mode] ? proceed : deny("Operation not allowed in " + mode),
  track: {
    add_to_history(ฮ“โ‚โ‚, op),
    store_results(ฮ“โ‚โ‚€, results) 
  },
  execute: ฮ›_ops[category][operation]()
}

Read the full file on GitHub ยท 144 lines

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 ยท 144 lines ยท 968 tokens per session scan A e9c8c1ac6b47

Subscribe to this mod's changes

mcp-websearch is a cursor rule published in the GitHub repository omril321/automated-notebooklm (15 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 968 tokens to every session, about $0.0048 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 2026-08-30.