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.
npx agentmods add rules/saveeit/savee-mcp-server/saveegit clone --depth 1 https://github.com/saveeit/savee-mcp-serverWhat 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 | $0.00026 | $0.00348 |
| Opus 5 | $0.00013 | $0.00174 |
| Sonnet 5 | $0.00005 | $0.00070 |
| Haiku 4.5 | $0.00003 | $0.00035 |
Grade A, and why
savee 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.
What it actually says
Savee
Savee is a curated visual-inspiration platform. The Savee MCP server exposes the user's own saves and boards, plus Savee's public library. All tools are read-only.
When to reach for it
- The user asks about what they've been saving, their boards, or their feed —
use
list_saves,list_boards,list_board_saves,list_feed. - The user wants references or a visual direction for something they haven't
saved yet — use
searchagainst the public library. Don't assume the answer is in their own collection. - The user asks about a board's direction, themes, or "the vibe" of a set of work — list it first, then look at it.
Looking vs. listing
The list and search tools return metadata only: title, source URL, dimensions, dominant colors. That is enough to spot themes by color or to hand back source links, and not enough to answer anything about composition, layout, type, or texture.
When the question is about what something looks like, call view_saves with
the id values from a previous result. Ask for the few saves that actually
matter, not a whole page — each one is an image in context.
Handing back results
Always include the original source URL when citing a save. That's what the user needs in order to go look at the real thing, and it credits the original work.
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.
- yesterday First seen · 37 lines · 26 tokens per session scan A bc2278b69844
savee is a cursor rule published in the GitHub repository saveeit/savee-mcp-server (0 stars, last pushed 7d ago), licensed MIT. It adds 26 tokens to every session and 348 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.
Other cursor rules, from other repositories
cursorrules
When the user asks you to implement a feature or fix an issue, use mooquickstart to atomically create and claim the task in a single step with complete specifications.
agentmemory
AgentMemory MCP server rules — use addmemory before answering any question that introduces a project-specific convention, dependency, or constraint.
cursorrules
This project uses Spectra for Spec-Driven Development(SDD).
blekline-chat-guard
Blekline chat guard — mask prompts via MCP and respect Cursor hook blocks.
designbrief
A library of 21 UI design direction files providing style guardrails for building tasteful interfaces.
cost-awareness
Cost-aware AI model selection guidance for Cursor Enterprise teams.