Gee Sweet

Name: Gee Sweet
Author: khuisman

@khuismanMCP server · External

MCP server for Google Workspace — Sheets, Drive, Docs (HTML or Markdown), and Calendar.

Calendarv0.9.1MITPython

Freeno charge per call

How to install

Runs on your machine from its package; the steps are below.

What it does

Reads
Writes
High impact

At most: creates or changes data: records, files, settings.

What it costs

Free

Odel charges nothing per call. The publisher may charge for its own service.

Runs locally over stdio

This server isn't hosted — your MCP client launches it from a package registry. Use one of the commands below, or drop the config into your client (e.g. Claude Desktop).

PyPImcp-gee-sweetv0.9.1

Run

uvx mcp-gee-sweet

MCP client config

{
  "mcpServers": {
    "gee-sweet": {
      "command": "uvx",
      "args": [
        "mcp-gee-sweet"
      ]
    }
  }
}

README4 min readView on GitHub

mcp-gee-sweet

The Google Workspace MCP server built for depth.

GitHub License

Google ships its own Sheets and Docs MCP servers now (Developer Preview), but they're shallow — thin CRUD, both approval-gated. mcp-gee-sweet goes deeper: raw formula access — reads =VLOOKUP() and friends directly, structural Docs support (colspan/rowspan tables, themes, named styles, an HTML/Markdown→AST→Docs pipeline), plus complete Drive and Calendar coverage Google's preview doesn't touch at all.

A few things no other Workspace MCP has:

Caching — repeated reads return in ~2ms from a local cache instead of a round-trip API call every time.
Formula access — reads raw =VLOOKUP(), =SUM(), and =IF() expressions, not just the values they produce.
Local sync — two-way sync between a local folder and Google Drive.

Install (stable):

bash

uvx mcp-gee-sweet

Install (bleeding edge — every code change on develop):

bash

uvx --prerelease=allow mcp-gee-sweet

Full documentation →

What's covered

Service	Tools	Google's own MCP	Highlights
Google Sheets	35	6	Formula access, batch read/write, 8 chart types, structural ops
Google Drive	38	—	File ops, sharing/permissions, local sync, revision history
Google Docs	34	2	Full HTML→Doc pipeline, tables, range styling, themes, Markdown export
Google Calendar	17	—	Event CRUD, free-slot finder across multiple calendars

Quick start

Option A: `uv` — local use and development

If you cloned the repo or just want to use the server from your machine, uv is all you need. No Docker required.

bash

git clone https://github.com/khuisman/mcp-gee-sweet.git
cd mcp-gee-sweet
uv sync

Then point your MCP client at it using stdio transport (see MCP client config below). The client spawns the server as a subprocess on demand — each session gets its own isolated process, so restarting the server for a code change or config update doesn't affect other open sessions.

Option B: Docker — persistent shared server (SSE)

Use Docker when you want a single long-running server that multiple clients connect to over SSE — for example, Claude Desktop talking to the same instance as Claude Code.

bash

git clone https://github.com/khuisman/mcp-gee-sweet.git
cd mcp-gee-sweet
make build   # build the container image
make start   # start the server (SSE on port 47000)
make logs    # tail logs

Point your MCP client at http://localhost:47000/sse.

Note: when using SSE, all clients share one server process. After a code change or restart (make restart), you must also restart each MCP client to reconnect.

Configuration

The server tries auth methods in a waterfall by default, OAuth first — it authenticates as you and has full personal Drive access, which is what local/dev use (Option A above) needs. For OAuth, download an OAuth Client ID JSON from GCP Console and point the server at it:

bash

export CREDENTIALS_PATH="/path/to/credentials.json"
export TOKEN_PATH="/path/to/token.json"
mcp-gee-sweet auth   # one-time browser login; `uvx mcp-gee-sweet auth` for a PyPI install

Pass the same CREDENTIALS_PATH and TOKEN_PATH in your MCP client's env. A stdio server with no token doesn't open a browser itself; its tools return an error telling you to run mcp-gee-sweet auth.

Service accounts (recommended for headless server deployments — see Option B above), base64 credential injection, and Application Default Credentials are also supported. See Authentication for all options.

MCP client config

Claude Desktop — stdio (cloned repo):

json

{
  "mcpServers": {
    "mcp-gee-sweet": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/mcp-gee-sweet", "mcp-gee-sweet"],
      "env": {
        "CREDENTIALS_PATH": "/path/to/credentials.json",
        "TOKEN_PATH": "/path/to/token.json"
      }
    }
  }
}

Claude Desktop — SSE (Docker):

json

{
  "mcpServers": {
    "mcp-gee-sweet": {
      "transport": "sse",
      "url": "http://localhost:47000/sse"
    }
  }
}

See Client Setup for more options including tool filtering.

Docs

Tools — full tool reference, grouped by domain
Authentication — all four auth methods
Configuration — env vars, caching, tool filtering
Client Setup — MCP client config examples
Design Principles — tool inclusion policy, composite tool decisions
Roadmap — planned features and known gaps

Contributing

See CONTRIBUTING.md for setup, QA workflows, and PR guidelines. A signed-off docs/qa/runs/vX.Y.Z.md record is required before any stable PyPI release — see docs/qa/README.md for the QA workflow.