Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add stevegustafson32/google-multi-account/plugin install google-multi-accountWrote 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/skills/stevegustafson32/google-multi-account/google-setup)<a href="https://agentmods.dev/skills/stevegustafson32/google-multi-account/google-setup"><img src="https://agentmods.dev/badge/skills/stevegustafson32/google-multi-account/google-setup.svg" alt="Measured on agentmods" 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 | $0.00084 | $0.01170 |
| Opus 5 | $0.00042 | $0.00585 |
| Sonnet 5 | $0.00017 | $0.00234 |
| Haiku 4.5 | $0.00008 | $0.00117 |
Grade A, and why
google-setup 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Multi-Account MCP — Setup & Troubleshooting
This plugin connects any number of Google accounts (Gmail + Calendar) to Claude via MCP.
Architecture (v0.2.0)
All files live in ~/.google-multi-mcp/:
~/.google-multi-mcp/
├── config.json # Account config + OAuth tokens
├── start.sh # Node auto-discovery launcher (called by Claude Desktop)
└── server/ # MCP server code
├── index.js # Main server — registers tools dynamically
├── auth.js # OAuth2 client manager
├── config.js # Config file reader/writer
├── gmail.js # Gmail API operations
├── calendar.js # Calendar API operations
├── package.json
├── node_modules/
└── scripts/
└── setup-tokens.js # Interactive OAuth setup
Claude Desktop config at ~/Library/Application Support/Claude/claude_desktop_config.json
points to /bin/bash ~/.google-multi-mcp/start.sh which finds node and launches the server.
Quick Setup
Run /setup for the fully guided experience. Or manually:
# 1. Copy files (if not already installed)
mkdir -p ~/.google-multi-mcp/server/scripts
# ... copy server files to ~/.google-multi-mcp/server/
# 2. Install dependencies
cd ~/.google-multi-mcp/server && npm install
# 3. Run OAuth setup
cd ~/.google-multi-mcp/server && node scripts/setup-tokens.js
# 4. Register in Claude Desktop config (see setup command for exact JSON)
# 5. Restart Claude (Cmd+Q → reopen)
How It Works
- Each account gets a custom label (e.g., "personal", "work", "client-acme")
- Credentials and tokens stored in
~/.google-multi-mcp/config.json - The MCP server dynamically builds Zod enum schemas from configured account labels
- Use
"all"as the account parameter to search/list across every account start.shsources NVM/volta/fnm/asdf before finding node — solves PATH issues
Health Check
Run these to diagnose issues:
# 1. Can node start the server?
cd ~/.google-multi-mcp/server && node -e "console.log('node OK')"
# 2. Does the server start?
cd ~/.google-multi-mcp/server && timeout 3 node index.js 2>&1; echo "exit: $?"
# 3. Does start.sh find node?
bash ~/.google-multi-mcp/start.sh 2>&1 & sleep 2; kill %1 2>/dev/null
# 4. Is it registered in desktop config?
cat ~/Library/Application\ Support/Claude/claude_desktop_config.json | grep google-multi
# 5. What do the MCP logs say?
grep -i "google-multi" ~/Library/Logs/Claude/mcp*.log | tail -20
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 133 lines · 84 tokens per session scan A 771965625549
google-setup is a skill published in the GitHub repository stevegustafson32/google-multi-account (2 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 1,170 once invoked, about $0.0004 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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.