10-mcp-tools

10-mcp-tools is a cursor rule for Cursor from MrG4dget/5e-tools-mcp. It costs 18 tokens per session (366 once invoked), scanned A, original, MIT.

A guide for choosing and using MCP tools that provide 5eTools data, such as rules, creatures, and spells. It explains which lookup tool to use and how to fetch or render the canonical result.

In plain words
What is it for?
Use it to search for entities, retrieve their full records, compare entries, find rules sections, render formatted results, and resolve inline tags.
Why use it?
It reduces guesswork and helps ensure answers come from the correct source and rules version.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it to search for entities, retrieve their full records, compare entries…

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/mrg4dget/5e-tools-mcp/10-mcp-tools
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.

Clone the repo
git clone --depth 1 https://github.com/MrG4dget/5e-tools-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.

agentmods badge for 10-mcp-tools

README.md
[![agentmods](https://agentmods.dev/badge/rules/mrg4dget/5e-tools-mcp/10-mcp-tools.svg)](https://agentmods.dev/rules/mrg4dget/5e-tools-mcp/10-mcp-tools)
Your own site
<a href="https://agentmods.dev/rules/mrg4dget/5e-tools-mcp/10-mcp-tools"><img src="https://agentmods.dev/badge/rules/mrg4dget/5e-tools-mcp/10-mcp-tools.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 366 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00018 $0.00366
Opus 5 $0.00009 $0.00183
Sonnet 5 $0.00004 $0.00073
Haiku 4.5 $0.00002 $0.00037

Measured 6d ago against content hash 14e307dc6079, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

10-mcp-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 6d 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/10-mcp-tools.mdc · 38 lines

What it actually says

Tool Selection Guide

Use these tools instead of guessing:

  1. search_entities({ query, kinds?, sources?, ruleset?, limit? })

    • Use for name-based lookup or comparisons. The server fuzzy-ranks results.
    • Include kinds and ruleset: "2024" when you need the 2024 version.
  2. get_entity({ uri? | key, format? })

    • Fetch the canonical record. Prefer format: "markdown" for chat-ready text.
  3. render_entries({ entries })

    • Convert 5eTools entries and inline {@tags} to Markdown/HTML.
  4. list_sources({ ruleset?, kind? })

    • Discover available sources (e.g., xPHB/xDMG/xMM).
  5. get_rules_section({ slugOrTitle, ruleset? })

    • Pull glossary/rules text by title/slug. Prefer 2024 unless told otherwise.
  6. resolve_tag({ tag })

    • Normalize inline tags (e.g., {@spell fireball|PHB}) to canonical URIs.

Return Shape Expectations

  • search_entities returns resource_link items. Use the URI(s) with get_entity as needed.
  • get_entity with format:"json" returns structured data; with "markdown" returns rendered text.

Patterns

  • Comparisons: call search_entities then get_entity for each candidate and produce a table.
  • Disambiguation: if multiple sources match, prefer 2024 by default.

@README.md

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. 6d ago First seen · 38 lines · 18 tokens per session scan A 14e307dc6079

Subscribe to this mod's changes

10-mcp-tools is a cursor rule published in the GitHub repository MrG4dget/5e-tools-mcp (2 stars, last pushed 1y ago), licensed MIT. It adds 18 tokens to every session and 366 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.