mcp-server-cantrip: Instructions file for Claude Code

CLAUDE.md

mcp-server-cantrip CLAUDE.md is an instructions file for Claude Code from ozten/mcp-server-cantrip. It costs 590 tokens per session, scanned A, original, MIT.

A set of project instructions for the Cantrip MCP server, which forwards tool requests to a Cantrip service. It explains the TypeScript project structure, API-key identity, and project context file.

In plain words
What is it for?
Use it when maintaining or extending the Cantrip MCP server, its 17 tool definitions, or its request client.
Why use it?
It helps an agent change the connector without putting business logic in the wrong place or passing team and project details incorrectly.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is ozten/mcp-server-cantrip's own configuration. It tells Claude Code how to work on mcp-server-cantrip itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-server-cantrip configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ozten/mcp-server-cantrip. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ozten/mcp-server-cantrip/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ozten/mcp-server-cantrip

Made for: Claude Code.

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 mcp-server-cantrip CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ozten/mcp-server-cantrip/claude-md/github.svg)](https://agentmods.dev/instructions/ozten/mcp-server-cantrip/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ozten/mcp-server-cantrip/claude-md"><img src="https://agentmods.dev/badge/instructions/ozten/mcp-server-cantrip/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.

agentmods 80×15 button for mcp-server-cantrip CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ozten/mcp-server-cantrip/claude-md"><img src="https://agentmods.dev/badge/instructions/ozten/mcp-server-cantrip/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 590 This file is loaded in full into every session.
When invoked 590 The same file — it is already loaded in full.
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 $0.00590 $0.00590
Opus 5.5 $0.00236 $0.00236
Sonnet 5.5 $0.00118 $0.00118
Haiku 4.5 $0.00059 $0.00059

Measured 2mo ago against content hash 05ea1c704ebc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-server-cantrip 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.

CLAUDE.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mcp-server-cantrip

What This Is

MCP server for the Cantrip GTM engine. Thin translation layer: MCP tool calls -> {command, args, flags} HTTP POST -> cantrip daemon. Zero business logic.

Tech Stack

  • TypeScript, Node.js
  • @modelcontextprotocol/sdk v1.x (stdio transport)
  • zod for parameter schemas

Structure

src/
  index.ts    # Entry point, MCP server setup, tool registration loop
  client.ts   # HTTP client — postCantrip() + .cantrip.json context
  tools.ts    # All 17 tool definitions (shape + handler)
  types.ts    # CantripRequest/CantripResponse types

Identity Model

  • CANTRIP_API_KEY — env var in MCP server config. Sent as Authorization: Bearer header. Identifies user → resolves team server-side.
  • .cantrip.json — per-project file in the working directory. Contains {"project": "my-saas"}. Read automatically on every request. Written by cantrip_init and cantrip_connect.

Agents never pass team or project as tool parameters. Context is ambient.

Key Principle

Every tool handler is ~5 lines: validate params -> build {command, args, flags} -> POST to daemon -> return JSON. If you're adding business logic here, it belongs in the daemon instead.

Adding a New Tool

  1. Add a ToolDef entry in tools.ts
  2. Define the shape (raw Zod fields, NOT wrapped in z.object())
  3. Implement handler that calls postCantrip(command, args, flags)
  4. The registration loop in index.ts picks it up automatically

Versioning & Releases

  • Single source of truth: package.json holds the version. src/index.ts imports it at runtime via createRequire. Never hardcode a version string elsewhere.
  • Bump before publish: Always bump the version before npm publish. Use ./scripts/release.sh [patch|minor|major] (default: patch).
  • What the script does: checks for clean working tree, runs npm version, builds, commits, and tags. It prints the git push and npm publish commands for you to run manually.
  • Current convention: patch bumps (1.0.x) for fixes and new tools. Minor/major for breaking changes or large features.

Read the full file on GitHub · 58 lines

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. 2mo ago First seen · 58 lines · 590 tokens per session scan A 05ea1c704ebc

Subscribe to this mod's changes

mcp-server-cantrip CLAUDE.md is an instructions file published in the GitHub repository ozten/mcp-server-cantrip (1 stars, last pushed 8mo ago), licensed MIT. It adds 590 tokens to every session, about $0.0024 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.

Related

mcp-server-cantrip CLAUDE.md compared with instructions from other repositories

mcp-server-cantrip CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-server-cantrip CLAUDE.mdozten/mcp-server-cantripInstructions file18mo agoMITA590Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot
generative-ai-for-beginners AGENTS.mdmicrosoft/generative-ai-for-beginnersInstructions file124ktodayMITA2,981Codex, OpenCode