New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice

MCP Google Workspace

26 tools. 16 can modify or destroy data without limits.

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

Last updated:

16 can modify or destroy data
10 read-only
26 tools total

Community server · catalogue entry checked 03/10/2026

How to control MCP Google Workspace ↓

What MCP Google Workspace exposes to your agents

Read (10) Write / Execute (12) Destructive / Financial (4)
Critical Risk

The most dangerous MCP Google Workspace tools

16 of MCP Google Workspace's 26 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control MCP Google Workspace

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Google Workspace, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations
{
  "delete-contact": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

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

Rate limit write operations
{
  "batch-update-emails": {
    "limits": [
      {
        "counter": "batch-update-emails_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "get-contact": {
    "limits": [
      {
        "counter": "get-contact_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

  1. Create a free account and register MCP Google Workspace — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON MCP GOOGLE WORKSPACE →

Instant setup, no code required.

All 26 MCP Google Workspace tools

WRITE 12 tools
Write batch-update-emails Modify multiple emails labels/status. Returns: empty on success (no response body). Use when: bulk operations Write create-contact Create new contact. Returns: created contact with resourceName, etag, metadata. Use when: adding new person to Write create-draft Create unsent email draft. Returns: draft id and message. Use when: composing email for later editing/sending. Write create-event Create calendar event. Returns: created event with id, htmlLink, start, end, status. Use when: scheduling new Write create-label Create custom label. Returns: new label with id, name, type= Write send-draft Send saved draft. Returns: sent message with id, threadId, labelIds. Use when: sending previously created draf Write send-email Send new email or reply. Returns: sent message id and threadId. Use when: composing new email or replying to t Write update-contact Modify existing contact. Returns: updated contact with new etag. Use when: changing contact details. Note: req Write update-draft Modify existing draft. Returns: updated draft with id, message. Use when: editing unsent draft content. Note: Write update-email Modify single email labels/status. Returns: updated message with new labelIds. Use when: marking one email rea Write update-event Modify existing event. Returns: updated event with id, summary, start, end. Use when: rescheduling, changing d Write update-label Modify label properties. Returns: updated label. Use when: renaming labels, changing visibility. Note: can

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

Questions about MCP Google Workspace

Can an AI agent delete data through the MCP Google Workspace MCP server? +

Yes. The MCP Google Workspace server exposes 4 destructive tools including delete-contact, delete-email, delete-event. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through MCP Google Workspace? +

The MCP Google Workspace server has 12 write tools including batch-update-emails, create-contact, create-draft. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach MCP Google Workspace.

How many tools does the MCP Google Workspace MCP server expose? +

26 tools across 3 categories: Destructive, Read, Write. 10 are read-only. 16 can modify, create, or delete data.

How do I enforce a policy on MCP Google Workspace? +

Register the MCP Google Workspace MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every MCP Google Workspace tool call.

Deterministic rules across all 26 MCP Google Workspace tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

26 MCP Google Workspace tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from MCP Google Workspace's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.