Borrowing it
Nothing to install: this file belongs to cyanheads/calculator-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/cyanheads/calculator-mcp-server/main/CLAUDE.mdgit clone --depth 1 https://github.com/cyanheads/calculator-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/cyanheads/calculator-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/cyanheads/calculator-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/cyanheads/calculator-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/cyanheads/calculator-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/cyanheads/calculator-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 | $0.06330 | $0.06330 |
| Opus 5 | $0.03165 | $0.03165 |
| Sonnet 5 | $0.01266 | $0.01266 |
| Haiku 4.5 | $0.00633 | $0.00633 |
Grade A, and why
calculator-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 8d 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.
This is a copy
83% identical to obsidian-mcp-server AGENTS.md — 364 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 427 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Protocol
Server: calculator-mcp-server
Version: 0.4.1
Framework: @cyanheads/mcp-ts-core ^0.12.3
Engines: Bun ≥1.3.0, Node ≥24.0.0
MCP SDK: @modelcontextprotocol/server 2.0.0
Zod: 4.4.3
Read the framework docs first:
node_modules/@cyanheads/mcp-ts-core/CLAUDE.mdcontains the full API reference — builders, Context, error codes, exports, patterns. This file covers server-specific conventions only.
A publicly-hosted calculator MCP server that lets any LLM verify mathematical computations. Powered by math.js v15. No auth required — all operations are read-only and stateless.
MCP Surface
| Primitive | Name | Purpose |
|---|---|---|
| Tool | calculate |
Evaluate, simplify, or differentiate math expressions. Single tool — operation param defaults to evaluate. |
| Resource | calculator://help |
Static reference of available functions, operators, constants, and syntax. |
Security Model
MathService wraps a hardened math.js instance — dangerous functions (import, createUnit, evaluate, parse, compile, chain, config, resolve, reviver, parser) are disabled in the expression scope. simplify and derivative are also disabled in expressions but called programmatically by the tool handler. Evaluation runs inside vm.runInNewContext() with a timeout. Input length is capped. Expression separators (semicolons and newlines) are rejected — single expression per call only (the separator scan is string-literal-aware so ; inside "..." is not treated as a statement break). Variable scope accepts z.record(z.number()) only with prototype-polluting keys blocked. Result types are validated (functions, parsers, and result sets rejected). .toString() / .toLocaleString() access on any value is rejected at parse time via an AST check — these method calls on function-valued identifiers would otherwise bypass the result-type guard by returning source as a plain string. Result size is capped via CALC_MAX_RESULT_LENGTH. The math.js version constant is redacted to prevent fingerprinting.
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.
- 8d ago First seen · 427 lines · 6,330 tokens per session scan A a8b0a580bc62
calculator-mcp-server CLAUDE.md is an instructions file published in the GitHub repository cyanheads/calculator-mcp-server (1 stars, last pushed 17d ago), licensed Apache-2.0. It adds 6,330 tokens to every session, about $0.0316 per session on Opus 5. A static security scan graded it A with 0 findings. It is 83% identical to obsidian-mcp-server AGENTS.md, differing in 364 lines, and is treated as a copy.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.