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/omril321/automated-notebooklmWrote 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/omril321/automated-notebooklm/mcp-websearch)<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>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 | $0.00968 | $0.00968 |
| Opus 5 | $0.00484 | $0.00484 |
| Sonnet 5 | $0.00194 | $0.00194 |
| Haiku 4.5 | $0.00097 | $0.00097 |
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.
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.
๐ Web Search MCP Integration for CursorRIPER ฮฃ
Symbol: ฮ (Lambda)
Version: 1.0.0
๐ Service Definition
service = "Web Search Operations"
symbol = "ฮ"
requires = "@modelcontextprotocol/server-brave-search"
๐ง 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"
}
}
๐ Mode Restrictions
Mฮ = {
ฮฉโ: [search_*, fetch_*], # RESEARCH: full access
ฮฉโ: [search_*, fetch_*], # INNOVATE: full access
ฮฉโ: [search_*, fetch_*, cache_*], # PLAN: search + cache
ฮฉโ: [], # EXECUTE: NO SEARCH (maintain focus!)
ฮฉโ
: [search_web, fetch_url] # REVIEW: verification only
}
๐ Permission Matrix
โฮ = {
create: [ฮฉโ], # Only PLAN can cache
read: [ฮฉโ, ฮฉโ, ฮฉโ, ฮฉโ
], # No reading in EXECUTE
update: [], # No updates
delete: [ฮฉโ] # Only PLAN can clear cache
}
๐ Context Tracking
ฮโโ = search_results[] = {
query: string,
results: [{title, url, snippet}],
timestamp: ISO8601,
mode: current_ฮฉ
}
ฮโโ = search_history[] = {
queries: [string],
counts: {per_mode: {ฮฉโ: n, ฮฉโ: n, ...}},
last_search: timestamp
}
ฮ_search_cache = Map<query, results>
โก Command Shortcuts
Sฮ = {
!ws: "brave_web_search",
!wl: "brave_local_search",
!wf: "fetch_url",
!wc: "clear search cache",
!wh: "show search history"
}
๐ก๏ธ Protection Levels
ฮจฮ = {
fetch_url: ฮจโ, # INFO - external content
clear_cache: ฮจโ # DEBUG - cache management
}
๐ Mode-Specific Behaviors
apply_search_op(op, mode) = {
check: mode === ฮฉโ ? deny("No search in EXECUTE mode!") : continue,
validate: op โ Mฮ[mode] ? proceed : deny("Operation not allowed in " + mode),
track: {
add_to_history(ฮโโ, op),
store_results(ฮโโ, results)
},
execute: ฮ_ops[category][operation]()
}
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.
- 7d ago First seen ยท 144 lines ยท 968 tokens per session scan A e9c8c1ac6b47
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.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.