AI agents use update-doc to create or update resources in MCP-Google-Doc — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP-Google-Doc environment.
Update operations modify data but are reversible—changes can be undone or reverted. This falls under Write rather than Destructive (which requires irreversibility). The severity is medium because unauthorized document updates could leak sensitive information or corrupt collaborative work, but the impact is limited to a single document and reversible.
From the tool's definition Tool name is 'update-doc' and server description states the MCP server enables 'updating documents'. The tool modifies existing Google Docs content reversibly.
Documented attack patterns abuse exactly the kind of access update-doc gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP-Google-Doc, and nothing reaches the server without passing your rules. This is the rule we recommend for update-doc:
{
"version": "1",
"default": "deny",
"tools": {
"update-doc": {
"limits": [
{
"counter": "update-doc_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update-doc 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.
Free to start. No card required.
update-doc. It is categorised as a Write tool in the MCP-Google-Doc MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP-Google-Doc MCP server in PolicyLayer and add a rule for update-doc: 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 MCP-Google-Doc. Nothing to install.
update-doc is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update-doc 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.
Set action: deny in the PolicyLayer policy for update-doc. 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.
update-doc is provided by the MCP-Google-Doc MCP server (ophydami/mcp-google-doc). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 8 MCP-Google-Doc tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
8 MCP-Google-Doc tools catalogued and risk-classified — across an index of 42,500+ MCP servers.