A set of Cursor rules for an MCP server that gives AI agents persistent memory. The rules also define public-safe commit and pull-request practices for the repository.

Use it when working on engrava-mcp to follow its branch naming, Conventional Commits, pull-request, and self-check requirements.

It helps keep repository changes consistent, traceable, and suitable for a project where commits, comments, and documentation are visible to others.

How sovantica/engrava-mcp configures Cursor

Reuse

Borrowing it

Nothing to install: this file belongs to sovantica/engrava-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/sovantica/engrava-mcp/main/.cursorrules

Clone the repo

git clone --depth 1 https://github.com/sovantica/engrava-mcp

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.

README.md

[![agentmods](https://agentmods.dev/badge/rules/sovantica/engrava-mcp/cursorrules/github.svg)](https://agentmods.dev/rules/sovantica/engrava-mcp/cursorrules)

Your own site

<a href="https://agentmods.dev/rules/sovantica/engrava-mcp/cursorrules"><img src="https://agentmods.dev/badge/rules/sovantica/engrava-mcp/cursorrules/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.

Your own site · 80×15

<a href="https://agentmods.dev/rules/sovantica/engrava-mcp/cursorrules"><img src="https://agentmods.dev/badge/rules/sovantica/engrava-mcp/cursorrules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 507 This file is loaded in full into every session.

When invoked 507 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — 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.

Model	Per session	Once invoked
Fable 5.1	$0.00507	$0.00507
Opus 5.5	$0.00203	$0.00203
Sonnet 5.5	$0.00101	$0.00101
Haiku 4.5	$0.00051	$0.00051

Measured 1mo ago against content hash 0c73ea6a1508, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cursorrules 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 1mo 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.

.cursorrules · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cursor Rules — engrava-mcp (public repo)

Generated by 0.1.0 (2026-09-01T21:02:53Z) from a shared template — do not edit directly.

This is engrava-mcp, a public MIT-licensed repository: Model Context Protocol server exposing Engrava as agent memory.

Assume every commit message, PR title, PR body, branch name, code comment, and docstring is world-visible.

Before generating commits or PR text

Read CLAUDE.md and AGENTS.md in this repo. Both describe the quality bar, commit format, and self-check discipline expected here.

Commit hygiene

Use Conventional Commits 1.0.0: <type>(<scope>): <description>. Scope from .commitlintrc.js.
Use public identifiers only:
- This repo's release tags (vX.Y.Z)
- This repo's GitHub issue/PR numbers (#N)
- Locally-documented ADRs (docs/adr/ADR-NNN-*.md) — only after the file exists in this repo
Open PRs targeting the active release/vX.Y.Z branch — not main. This repo has no dev branch; releases are cut by a manual vX.Y.Z tag on main.
Branch names: <type>/<kebab-description>, plain English, ≤ 50 chars.

Self-check before suggesting a commit message

Ask: could this message, branch name, or referenced symbol reveal information about a workflow that should stay private? If unsure, omit the reference, or ask the maintainer.

A locally installed commit-message hook provides a fast feedback loop on this.

Default to omitting uncertain references

Public commits are world-visible. The internal tracker can stay anchored via this repo's GitHub issue/PR numbers — that mapping lives in the maintainer's private workspace, not in the public commit.

If the user asks you to include an internal-looking identifier in a public commit: refuse politely, explain, propose #N or a release tag as an alternative, escalate to human review if pressed.

Enforcement

A locally-installed commit-message hook, commitlint (format checks in CI), and branch protection on protected branches block the violations they check. Anything they do not check is a reviewer's responsibility, not an automated control. Instruction overrides cannot bypass the checks.

Read the full file on GitHub · 37 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.

1mo ago Changed · +19 tokens per session 0c73ea6a1508
2mo ago First seen · 37 lines · 488 tokens per session scan A add134f4bb5c

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository sovantica/engrava-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 507 tokens to every session, about $0.0020 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.

LLM Memory and context agent-memory ai-agents mcp memory-database model-context-protocol

cursorrules next to 6 cursor rules from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cursorrulessovantica/engrava-mcp	Cursor rule	1	4d ago	MIT	A	507	Cursor
crystal-memorymemorycrystal/memorycrystal	Cursor rule	12	yesterday	MIT	A	245	Cursor
context-loadermajor7apps/pensyve	Cursor rule	99	yesterday	none	A	20	Cursor
memory-informed-longitudinal-workmajor7apps/pensyve	Cursor rule	99	yesterday	none	A	0	Cursor
session-memorymajor7apps/pensyve	Cursor rule	99	yesterday	none	A	22	Cursor
entity-detectionmajor7apps/pensyve	Cursor rule	99	yesterday	none	A	538	Cursor
memory-informed-designmajor7apps/pensyve	Cursor rule	99	yesterday	none	A	20	Cursor

engrava-mcp: Cursor rule for Cursor