cursorrules

A set of project rules that tells an agent which rag-knowledge-graph-mcp tools to use for knowledge-graph questions. A knowledge graph stores information as connected entities and relationships, while RAG retrieves relevant stored content to answer questions.

In plain words
What is it for?
Indexing documents, searching retrieved knowledge, adding relationships between entities, querying the graph, and checking knowledge statistics.
Why use it?
It gives the agent a defined tool-selection rule instead of leaving it to guess how to handle these requests.

Cursor rule for Cursor

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.

agentmods
npx agentmods add rules/csoai-org/rag-knowledge-graph-mcp/cursorrules
Clone the repo
git clone --depth 1 https://github.com/CSOAI-ORG/rag-knowledge-graph-mcp

Made for: Cursor.

Per session 84 This file is loaded in full into every session.
When invoked 84 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00084 $0.00084
Opus 5 $0.00042 $0.00042
Sonnet 5 $0.00017 $0.00017
Haiku 4.5 $0.00008 $0.00008

Measured 2d ago against content hash 4ed62ab26650, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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 · 10 lines

What it actually says

rag-knowledge-graph-mcp - Auto-trigger Rules

When the user asks about rag knowledge graph, use rag-knowledge-graph-mcp tools: index_document, rag_query, add_graph_edge, graph_query, get_knowledge_stats

MCP server for rag knowledge graph mcp operations

Install: pip install rag-knowledge-graph-mcp

By MEOK AI Labs — MIT licensed.

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. 2d ago First seen · 10 lines · 84 tokens per session scan A 4ed62ab26650

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository CSOAI-ORG/rag-knowledge-graph-mcp (0 stars, last pushed 4d ago), licensed MIT. It adds 84 tokens to every session, about $0.0004 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.