gmail_create_filter · Mariana Google MCP: Risk & Policy

WHAT IT DOES

What gmail_create_filter does on Mariana Google MCP

AI agents use gmail_create_filter to create or update resources in Mariana Google MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mariana Google MCP environment.

WHY IT NEEDS A POLICY

Why gmail_create_filter needs a policy

Creating a filter is a Write operation—it persists new configuration in Gmail that alters how messages are processed going forward. While reversible (the filter can be deleted later), it immediately commits a change to email handling. Severity is medium because filters automatically process emails based on criteria, but the server provides 'safety-first interface with comprehensive mutation logging' mitigations.

From the tool's definition Tool description states it 'Create[s] a Gmail filter rule' that 'applies actions automatically,' indicating it modifies Gmail configuration irreversibly by adding a new filter.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

gmail_create_filter Rate-limited

gmail_create_filter stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "gmail_create_filter": {
      "limits": [
        {
          "counter": "gmail_create_filter_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Mariana Google MCP, so you can run agents against it safely.

FAQ

Questions about gmail_create_filter

What does the gmail_create_filter tool do? +

Create a Gmail filter rule. Matches messages by criteria and applies actions automatically. At least one criterion and one action required. It is categorised as a Write tool in the Mariana Google MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on gmail_create_filter? +

Register the Mariana Google MCP server in PolicyLayer and add a rule for gmail_create_filter: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mariana Google MCP. Nothing to install.

What risk level is gmail_create_filter? +

gmail_create_filter is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit gmail_create_filter? +

Yes. Add a rate_limit block to the gmail_create_filter rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block gmail_create_filter completely? +

Set action: deny in the PolicyLayer policy for gmail_create_filter. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides gmail_create_filter? +

gmail_create_filter is provided by the Mariana Google MCP server (marianasmall/mariana-google-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.