Borrowing it
Nothing to install: this file belongs to sandeepgandhi500/dice-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sandeepgandhi500/dice-mcp-server/main/CLAUDE.mdgit clone --depth 1 https://github.com/sandeepgandhi500/dice-mcp-serverWrote 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.
[](https://agentmods.dev/instructions/sandeepgandhi500/dice-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/sandeepgandhi500/dice-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/sandeepgandhi500/dice-mcp-server/claude-md/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.
<a href="https://agentmods.dev/instructions/sandeepgandhi500/dice-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/sandeepgandhi500/dice-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00710 | $0.00710 |
| Opus 5.5 | $0.00284 | $0.00284 |
| Sonnet 5.5 | $0.00142 | $0.00142 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
dice-mcp-server CLAUDE.md 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - Dice Roller MCP Server
Implementation Overview
This is a self-contained MCP server with no external API dependencies — everything runs on Python's built-in random module. It exposes 5 tools for coin flips, standard dice notation, and D&D-specific roll mechanics.
Server Details
- Server name:
dice - File:
dice_server.py - Transport: stdio
- External dependencies: none beyond
mcp[cli]
Tools
| Tool | Parameters | Description |
|---|---|---|
flip_coin |
times: str = "1" |
Flips 1+ coins, returns Heads/Tails and a summary if more than one |
roll_dice |
notation: str = "1d20" |
Parses NdM, NdM+K, NdM-K notation and returns individual rolls + total |
roll_advantage |
modifier: str = "0" |
Rolls 2d20, keeps the higher, applies modifier |
roll_disadvantage |
modifier: str = "0" |
Rolls 2d20, keeps the lower, applies modifier |
roll_ability_scores |
count: str = "6" |
Rolls 4d6 drop-lowest per score, for count scores |
Design Decisions
- No
typingimports, single-line docstrings, string-only params: follows the gateway compatibility rules to avoid panics in Claude Desktop. - Dice notation parsing via regex:
parse_dice_notation()usesre.fullmatch(r"(\d*)d(\d+)([+-]\d+)?", ...)to support the commonNdM+Kshorthand DMs and players use at the table. - Sane limits: capped at 100 dice per roll, 1000 sides per die, and 100 coin flips per call, to avoid pathological inputs (e.g. someone requesting a million-sided die).
- Every tool returns a formatted string with emoji markers (🪙 🎲 📊 ✅ ❌) for quick visual scanning, per the output formatting conventions.
roll_ability_scoresshows its work: displays each individual d6 roll and which die was dropped, so results are auditable/transparent for tabletop use.
Adding a New Tool
- Add a new
async deffunction decorated with@mcp.tool(). - Keep the docstring to a single line — multi-line docstrings break the gateway.
- Use
param: str = ""defaults, neverNoneor typed defaults. - Validate input with
.strip()checks, not truthiness checks. - Wrap logic in
try/exceptand return a❌ Error: ...string on failure. - Rebuild the Docker image and update the custom catalog's
tools:list.
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.
- 2mo ago First seen · 52 lines · 710 tokens per session scan A 59e3fac64935
dice-mcp-server CLAUDE.md is an instructions file published in the GitHub repository sandeepgandhi500/dice-mcp-server (0 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 710 tokens to every session, about $0.0028 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.
dice-mcp-server CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dice-mcp-server CLAUDE.mdsandeepgandhi500/dice-mcp-server | Instructions file | 0 | 4mo ago | Apache-2.0 | A | 710 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 8,130 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 283k | today | MIT | A | 4,342 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 3,153 | GitHub Copilot |