An MCP server to interact with GAM7 for Google Workspace administration
Project description
GAM MCP Server
This is a Model Context Protocol (MCP) server that empowers an AI IDE, terminal, or agent to perform administrative actions on Google Workspace using an existing local installation of GAM7.
Prerequisites
- Python 3.10+ (managed via
uvor installed globally) - GAM7: Installed and fully authenticated with a
client_secrets.jsonandoauth2.txt/oauth2service.json. - uv: The ultra-fast Python package installer and resolver.
Environment Variables
The server relies on the following environment variables to locate and run your local GAM installation:
GAM_EXECUTABLE_PATH(optional): The absolute path to your localgamexecutable. Ifgamis already in yourPATH, you can leave this unset, and the server will executegamdirectly.GAM_CFG_DIR(optional): The absolute path to the directory containing your GAM configuration and authentication files (e.g.oauth2.txt,client_secrets.json). If left unset, GAM will use its default configuration paths.
Installation and Usage
To run the server with uv:
uv run src/gamcp/server.py
Usage with Claude Desktop, Gemini Enterprise, or other MCP clients
Add the following to your claude_desktop_config.json:
Important: Claude Desktop often does not inherit your full system path. If you used the standalone installer for
uv(which places it in~/.local/binor~/.cargo/bin), you will likely receive a "Failed to spawn process" error. To fix this, replace"uv"or"uvx"in thecommandfield with the absolute path to the executable (e.g.,"/Users/YOUR_USER/.local/bin/uvx"or"/opt/homebrew/bin/uvx").
Running locally (Development & Cloning)
If you've cloned this repository locally, you can use uv run:
{
"mcpServers": {
"gamcp": {
"command": "/absolute/path/to/uv",
"args": [
"--directory",
"/absolute/path/to/gamcp",
"run",
"src/gamcp/server.py"
]
}
}
}
Easy installation (Global standard)
If you have published this package to PyPI or installed it globally via uv tool install, you can use uvx directly, which runs isolated tools reliably.
{
"mcpServers": {
"gamcp": {
"command": "/absolute/path_to/.local/bin/uvx",
"args": [
"gamcp"
]
}
}
}
Note: In most cases, the MCP server will automatically detect the standard location GAM or GAMADV-XTD3 installers place their configuration and executable files into. If you installed GAM in a non-standard location, you can additionally supply the GAM_EXECUTABLE_PATH or GAM_CFG_DIR variables in the env dictionary block.
Tools
The server exposes a comprehensive suite of tools organized by functional area:
Core Operations
run_gam_command(args: list[str]): Executes raw GAM commands. Provide arguments as a list of strings (e.g.,["info", "domain"]). Returns standard output and standard error.validate_gam_command(args: list[str]): Validates the structure of a proposed GAM command without executing it.
Bulk Processing
build_bulk_gam_command(...): Constructs a GAM bulk processing command from structured inputs without executing it.bulk_process_from_sheet(...): Executes a GAM bulk command using a Google Sheet as the data source.
Google Drive
migrate_folder_to_shared_drive(...): Migrates a Google Drive folder to a Shared Drive.get_permissions_to_sheet(...): Retrieves file/folder/shared drive permissions and writes them to a Google Sheet.
Calendar
transfer_calendar_event(...): Transfers a calendar event from one user to another.
Groups
create_collaborative_inbox_group(...): Creates a new Google Group configured as a Collaborative Inbox.get_group_permissions_to_sheet(...): Retrieves group members and their roles, outputting to a Google Sheet.
Users
create_gws_user(...): Creates a new Google Workspace user.identify_workspace_entity(identifier: str): Identifies a Workspace entity (user, group, alias, etc.) by its email or ID.
Reports
get_gmail_log_events(...): Retrieves Gmail log events and optionally writes them to a Google Sheet.get_user_email_count_to_sheet(...): Retrieves email counts for specific labels across multiple users.
Resources
The server provides the following resources:
gam://bulk-processing-guide: A reference guide for constructing GAM bulk processing commands. Includes details on source types, processing modes, column substitution syntax, and batch file directives.
Acknowledgements
This project uses documentation derived from the GAM7 project, which is licensed under the Apache License 2.0. GAM MCP Server is not affiliated with or endorsed by the GAM-team.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file gamcp-0.1.4.tar.gz.
File metadata
- Download URL: gamcp-0.1.4.tar.gz
- Upload date:
- Size: 71.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.10.4 {"installer":{"name":"uv","version":"0.10.4","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
c95e282364b2f1d339d6d8234ea975d994590508eb89bb518954f3b180666c0b
|
|
| MD5 |
cacb2c65c1092e13d895495839608dad
|
|
| BLAKE2b-256 |
52741754a798e779cbe4dd41591204c1e80e8280a6a46af5ab63c6c9c464e74d
|
File details
Details for the file gamcp-0.1.4-py3-none-any.whl.
File metadata
- Download URL: gamcp-0.1.4-py3-none-any.whl
- Upload date:
- Size: 32.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.10.4 {"installer":{"name":"uv","version":"0.10.4","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
49eced1f7a529152fcf808e1031df74dcd2be0826310822009e27032bcb0f095
|
|
| MD5 |
ba991788b9ccec6c0642818476708372
|
|
| BLAKE2b-256 |
8a3d954ef616117fe19186dcd01b854cd9d229bb2acaada22884c1a36ea66f4c
|