agy-mcp-server: Instructions file for Claude Code

CLAUDE.md

agy-mcp-server CLAUDE.md is an instructions file for Claude Code from toonPt0473/agy-mcp-server. It costs 1,083 tokens per session, scanned A, original, ISC.

A repository-specific instruction document named CLAUDE.md for an MCP server that connects Claude Code to Google Antigravity’s agy command-line tool. It records the project type, development commands, architecture, and important files.

In plain words
What is it for?
Use it when working on the agy MCP server, especially its TypeScript build, tests, command execution, tool definitions, handlers, and server behavior.
Why use it?
It gives coding agents the local context needed to build, test, lint, format, and change this repository consistently.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions Codex.

This is toonPt0473/agy-mcp-server's own configuration. It tells Claude Code how to work on agy-mcp-server 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 agy-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to toonPt0473/agy-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.

Copy the file
curl -O https://raw.githubusercontent.com/toonPt0473/agy-mcp-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/toonPt0473/agy-mcp-server

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 agy-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/toonpt0473/agy-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/toonpt0473/agy-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/toonpt0473/agy-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/toonpt0473/agy-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.

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/toonpt0473/agy-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/toonpt0473/agy-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,083 This file is loaded in full into every session.
When invoked 1,083 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 $0.01083 $0.01083
Opus 5 $0.00541 $0.00541
Sonnet 5 $0.00217 $0.00217
Haiku 4.5 $0.00108 $0.00108

Measured 8d ago against content hash 5623c9c342ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

agy-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.

CLAUDE.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file guides Claude Code when working in this repository.

Repository Type

An MCP (Model Context Protocol) server that wraps Google Antigravity's agy CLI, exposing it as tools to Claude Code and other MCP clients. Sister project to codex-mcp-server (same architecture, different upstream CLI).

Development Commands

npm run build          # tsc -> dist/
npm run dev            # run src/index.ts with tsx
npm test               # jest (ESM via ts-jest)
npm run test:coverage  # coverage report
npx jest src/__tests__/agy-handler.test.ts   # single test file
npm run lint           # eslint
npm run format         # prettier

Architecture

MCP Client (Claude Code)
  -> StdioTransport
  -> AgyMcpServer (server.ts)
  -> ToolHandlers (tools/handlers.ts)
  -> executeCommand / executeCommandStreaming (utils/command.ts)
  -> agy CLI (print mode)
File Purpose
src/index.ts Entry point; starts AgyMcpServer
src/server.ts MCP server, list_tools / call_tool, progress notifications
src/tools/definitions.ts Tool schemas + annotations
src/tools/handlers.ts Tool logic (agy, models, ping, help, listSessions, changelog)
src/types.ts Types, Zod schemas, constants
src/session/storage.ts In-memory session storage
src/utils/command.ts Process spawning with stdin piping + streaming
src/utils/logger.ts Markdown conversation transcript logger (env-gated)
src/errors.ts Error classes

Critical implementation details

  • Prompt is the value of -p. agy -p "<prompt>" takes the prompt as the flag value. -p REQUIRES a value — a bare -p errors with "flag needs an argument". agy only falls back to reading stdin when -p is empty. The handler passes the prompt via cmdArgs.push('-p', prompt), and command.ts always closes stdin so agy never blocks waiting for input.
  • Answer is on stdout. agy print mode writes the response to stdout (exit 0). Handlers still fall back to stderr for robustness.
  • Model selection (agy v1.0.5+). agy --model "<name>" picks the model for a call; agy models lists them. The model param maps to --model (arg > AGY_MCP_DEFAULT_MODEL env > omitted). Names contain spaces/parens and are safe as a single argv value (spawn uses no shell on POSIX). Unknown names are not rejected — agy falls back to its default. (Older agy ≤1.0.3 had no --model.)
  • No conversation ID in print mode. Multi-turn continuation uses agy --continue (most-recent conversation). --conversation <id> is only used when the caller supplies an explicit conversationId.
  • Conversation logging is env-gated and must never throw. logger.ts appends a Markdown transcript per agy call when AGY_MCP_LOG_DIR or AGY_MCP_LOG_FILE is set (off by default). Failures are caught and logged to stderr only — the tool result is unaffected.

Read the full file on GitHub · 90 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. 8d ago First seen · 90 lines · 1,083 tokens per session scan A 5623c9c342ea

Subscribe to this mod's changes

agy-mcp-server CLAUDE.md is an instructions file published in the GitHub repository toonPt0473/agy-mcp-server (1 stars, last pushed 3mo ago), licensed ISC. It adds 1,083 tokens to every session, about $0.0054 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.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens