// SCAN REPORT

Google Workspace Chat (gws CLI)

37 tools. 19 can modify or destroy data without limits.

5 destructive tools with no built-in limits. Policy required.

Last updated: 5 Apr 2026

19 can modify or destroy data

18 read-only

37 tools total

// TOOL MAP

Read (18) Write / Execute (14) Destructive / Financial (5)

// WHAT CAN GO WRONG

Destructive tools (chat_customEmojis_delete, chat_spaces_delete, chat_spaces_members_delete) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.

Write operations (chat_customEmojis_create, chat_media_upload, chat_spaces_completeImport) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.

One command. Full control.

Intercept sits between your agent and Google Workspace Chat (gws CLI). Every tool call checked against your policy before it executes — so your agent can do its job without breaking things.

npx -y @policylayer/intercept scan -- npx -y @gws mcp -s chat

Scans every tool. Generates a policy. Starts enforcing.

Works with Claude Code · Cursor · Claude Desktop · Windsurf · any MCP client

// RECOMMENDED RULES

Deny destructive operations

chat_customEmojis_delete:
  rules:
    - action: deny

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

chat_customEmojis_create:
  rules:
    - rate_limit: 30/hour

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

chat_customEmojis_get:
  rules:
    - rate_limit: 60/minute

Controls API costs and prevents retry loops from exhausting upstream rate limits.

// ALL 37 GOOGLE WORKSPACE CHAT (GWS CLI) TOOLS

DESTRUCTIVE 5 tools

Destructive chat_customEmojis_delete Destructive chat_spaces_delete Destructive chat_spaces_members_delete Destructive chat_spaces_messages_delete Destructive chat_spaces_messages_reactions_delete

WRITE 14 tools

Write chat_customEmojis_create Write chat_media_upload Write chat_spaces_completeImport Write chat_spaces_create Write chat_spaces_members_create Write chat_spaces_members_patch Write chat_spaces_messages_create Write chat_spaces_messages_patch Write chat_spaces_messages_reactions_create Write chat_spaces_messages_update Write chat_spaces_patch Write chat_spaces_setup Write chat_users_spaces_spaceNotificationSetting_patch Write chat_users_spaces_updateSpaceReadState

READ 18 tools

Read chat_customEmojis_get Read chat_customEmojis_list Read chat_media_download Read chat_spaces_findDirectMessage Read chat_spaces_get Read chat_spaces_list Read chat_spaces_members_get Read chat_spaces_members_list Read chat_spaces_messages_attachments_get Read chat_spaces_messages_get Read chat_spaces_messages_list Read chat_spaces_messages_reactions_list Read chat_spaces_search Read chat_spaces_spaceEvents_get Read chat_spaces_spaceEvents_list Read chat_users_spaces_getSpaceReadState Read chat_users_spaces_spaceNotificationSetting_get Read chat_users_spaces_threads_getThreadReadState

// FAQ

Can an AI agent delete data through the Google Workspace Chat (gws CLI) MCP server? +

Yes. The Google Workspace Chat (gws CLI) server exposes 5 destructive tools including chat_customEmojis_delete, chat_spaces_delete, chat_spaces_members_delete. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Google Workspace Chat (gws CLI)? +

The Google Workspace Chat (gws CLI) server has 14 write tools including chat_customEmojis_create, chat_media_upload, chat_spaces_completeImport. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.

How many tools does the Google Workspace Chat (gws CLI) MCP server expose? +

37 tools across 3 categories: Destructive, Read, Write. 18 are read-only. 19 can modify, create, or delete data.

How do I add Intercept to my Google Workspace Chat (gws CLI) setup? +

One line change. Instead of running the Google Workspace Chat (gws CLI) server directly, prefix it with Intercept: intercept -c google-workspace-chat.yaml -- npx -y @@gws mcp -s chat. Download a pre-built policy from policylayer.com/policies/google-workspace-chat and adjust the limits to match your use case.

// RELATED SERVERS

Other MCP servers with similar tools.

Starter policies available for each. Same risk classification, same one-command setup.

policylayer/intercept

Control every MCP tool call
your agent makes.

Set budgets, approvals, and hard limits across MCP servers.

npx -y @policylayer/intercept init

Protect your agent in 30 seconds. Scans your MCP config and generates enforcement policies for every server.

Google Workspace Chat (gws CLI)

One command. Full control.

Other MCP servers with similar tools.

Control every MCP tool call your agent makes.

Control every MCP tool call
your agent makes.