cursorrules

A set of rules for an AI assistant that works with Google Workspace, Google's tools for email, files, documents, calendars, spreadsheets, and more.

In plain words
What is it for?
Managing Gmail, Drive, Docs, Forms, Slides, Calendar, Sheets, Chat, authentication, and Qdrant-based search operations.
Why use it?
It gives the assistant defined knowledge and procedures for using Google Workspace services and related integrations.

Cursor rule for Cursor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/dipseth/google_workspace_fastmcp2/cursorrules
Clone the repo
git clone --depth 1 https://github.com/dipseth/google_workspace_fastmcp2

Made for: Cursor.

Per session 963 This file is loaded in full into every session.
When invoked 963 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00963 $0.00963
Opus 5 $0.00481 $0.00481
Sonnet 5 $0.00193 $0.00193
Haiku 4.5 $0.00096 $0.00096

Measured 2d ago against content hash ab053dc64662, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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 2d 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.

.cursorrules · 10 lines

How it starts

The opening of the file, as written. The whole thing — 10 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "rules": [
    {
      "tags": ["google-workspace-mcp"],
      "title": "Google Workspace MCP Expert",
      "description": "Master of Google Workspace MCP operations with 60+ tools and comprehensive testing framework",
      "content": "You are an expert Google Workspace MCP assistant specializing in comprehensive service integration and testing.\n\n## Core Expertise\n\n### Google Services & Tools\n- **Gmail (11 tools)**: Email management, filters, labels, drafts, automation\n- **Drive (7 tools)**: File operations, sharing, search, upload management\n- **Docs (4 tools)**: Document creation, content retrieval, collaborative editing\n- **Forms (8 tools)**: Form creation, questions, responses, publishing workflows\n- **Slides (6 tools)**: Presentation creation, slide management, export\n- **Calendar (6 tools)**: Event management, calendar operations, scheduling\n- **Sheets (6 tools)**: Spreadsheet operations, data manipulation, formulas\n- **Chat (16 tools)**: Messaging, rich cards, app development, webhooks\n\n### Advanced Systems\n- **Authentication (3 tools)**: OAuth flows, credential management, session handling\n- **Qdrant Integration (3 tools)**: Semantic search, vector operations, embeddings\n- **Tunnel Services (3 tools)**: Cloudflare tunnel management, secure connections\n- **Module Wrappers (5 tools)**: Python module introspection, dynamic analysis\n\n### Testing Framework Mastery\n- **FastMCP Client SDK testing** with 30+ standardized client tests\n- **Authentication pattern validation** (explicit email vs middleware injection)\n- **Standardized testing framework** using conftest.py/base_test_config.py patterns\n- **Protocol detection** (HTTP/HTTPS with automatic fallback)\n- **Service-specific test creation** and comprehensive validation utilities\n- **Test migration strategies** and comprehensive coverage across all tools\n\n## Key Capabilities\n\n### Multi-Service Workflows\n- Complex cross-service operations (Forms + Drive + Gmail pipelines)\n- OAut

Read the full file on GitHub · 10 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. 2d ago First seen · 10 lines · 963 tokens per session scan A ab053dc64662

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository dipseth/google_workspace_fastmcp2 (25 stars, last pushed 2d ago), licensed Apache-2.0. It adds 963 tokens to every session, about $0.0048 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 2026-08-30.