tools

A set of coding rules for Python functions exposed as MCP tools. They require specific parameter types, method documentation, and examples of valid inputs.

In plain words
What is it for?
Use them when writing or reviewing Python functions marked with the MCP tool decorator, especially their parameters, defaults, docstrings, and examples.
Why use it?
They reduce ambiguous tool interfaces and make MCP tool functions easier for agents and users to call correctly.

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/gingerol/unrealengine-ai-mcp/tools
Clone the repo
git clone --depth 1 https://github.com/gingerol/UnrealEngine-ai-mcp

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 163 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00163
Opus 5 $0.00000 $0.00081
Sonnet 5 $0.00000 $0.00033
Haiku 4.5 $0.00000 $0.00016

Measured 2d ago against content hash 7351d1b5cd4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tools 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.

.cursor/rules/tools.mdc · 15 lines

What it actually says

Guidelines for using Python for MCP Tools

The following guidelines apply to any method or function marked with the @mcp.tool() decorator.

  • Parameters should not have any of the following types: Any, object, Optional[T], Union[T].
  • For a given parameter x of type T that has a default value, do not use type x : T | None = None. Instead, use x: T = None and handle defaults within the method body itself.
  • Always include method docstrings and make sure to given proper examples of valid inputs especially when no type hints are present.

When this rule is applied, please remember to explicitly mention it.

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 · 15 lines · 0 tokens per session scan A 7351d1b5cd4f

Subscribe to this mod's changes

tools is a cursor rule published in the GitHub repository gingerol/UnrealEngine-ai-mcp (5 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 163 tokens. 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.