gws-mcp-server: Instructions file for Claude Code

CLAUDE.md

gws-mcp-server CLAUDE.md is an instructions file for Claude Code from conorbronsdon/gws-mcp-server. It costs 915 tokens per session, scanned A, original, MIT.

Project instructions for gws-mcp-server, a service that lets an AI assistant use Google Drive, Sheets, Calendar, Docs, Gmail, and Tasks through the command-line tool gws.

In plain words
What is it for?
Use it when developing, testing, or debugging the server, its Google Workspace tools, file downloads, or Gmail draft creation.
Why use it?
It documents the system's structure, security requirements, platform-specific concerns, and testing expectations in one place.

Instructions file for Claude Code

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

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

Reuse

Borrowing it

Nothing to install: this file belongs to conorbronsdon/gws-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/conorbronsdon/gws-mcp-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/conorbronsdon/gws-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 gws-mcp-server CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/conorbronsdon/gws-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/conorbronsdon/gws-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 915 This file is loaded in full into every session.
When invoked 915 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 $0.00915 $0.00915
Opus 5.5 $0.00366 $0.00366
Sonnet 5.5 $0.00183 $0.00183
Haiku 4.5 $0.00092 $0.00092

Measured 15d ago against content hash 25ca3c2eb94d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gws-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 15d 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 · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

gws-mcp-server

MCP server that exposes Google Workspace CLI (gws) as Model Context Protocol tools.

Architecture

  • src/index.ts — MCP server bootstrap, Zod schema generation, tool registration. Also hosts custom tools that don't fit the declarative ToolDef pattern (listed in CUSTOM_TOOLS: drive_files_download, gmail_drafts_create, drive_permissions_transferOwnership, drive_permissions_proposeOwnershipTransfer).
  • src/services.ts — Declarative tool definitions across 8 services (drive, sheets, calendar, docs, slides, gmail, tasks, people). Each entry maps to a gws CLI command + params/body. DEFAULT_SERVICES is the no-flag set; people is supported but opt-in because it needs an extra OAuth scope.
  • src/executor.ts — Command builder and runner with security hardening (shell injection prevention, path validation).
  • src/errors.ts — Typed error hierarchy; mapGwsErrorToTyped() recovers a status code from gws's plain-text stderr.
  • src/auth.ts — gws-mcp-server auth login -s <services>: reads the saved credential's scopes from gws auth status, merges in the services' scopes and runs gws auth login --scopes <union> (gws's own -s replaces the credential, #68). Dispatched from main() when argv[2] is auth.
  • src/mime.ts — RFC 2822 builder + base64url encoding for gmail_drafts_create. Includes CRLF-injection guard on header values.
  • src/__tests__/ — Vitest tests: one file per source module, plus an in-memory MCP client suite, a Windows-only npm-shim argument round-trip, and a publish-workflow check.

Key constraints

  • gws is always spawned without a shell; on Windows src/windows-binary.ts resolves npm's gws.cmd to its JS entry point and runs it with Node
  • Custom tools (CUSTOM_TOOLS in index.ts) are registered by hand because they do work the declarative ToolDef shape can't express (file type detection, MIME building, request-body fields the caller must not be able to set)
  • All tools delegate to the gws CLI binary — no direct Google API calls
  • Gmail draft creation accepts user-controlled header values; src/mime.ts rejects CR/LF in any header input to prevent email header injection

Read the full file on GitHub · 45 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. 15d ago Changed · +2 lines · +136 tokens per session 25ca3c2eb94d
  2. 1mo ago Changed · +36 tokens per session ab8c2c8b54c0
  3. 1mo ago Changed · +5 lines · +231 tokens per session ed7ba7dd110d
  4. 2mo ago First seen · 38 lines · 512 tokens per session scan A a81470716ebd

Subscribe to this mod's changes

gws-mcp-server CLAUDE.md is an instructions file published in the GitHub repository conorbronsdon/gws-mcp-server (13 stars, last pushed 8d ago), licensed MIT. It adds 915 tokens to every session, about $0.0037 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

Other instructions, from other repositories

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 · 9,715 tokens

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 · 7,461 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens