AI agents use update_document to create or update resources in Forgetful — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Forgetful environment.
Updates to documents are reversible modifications—prior versions can typically be recovered or the document can be reverted. This is less severe than deletion (Destructive) but more impactful than reads. Medium severity reflects that uncontrolled document updates could corrupt a knowledge base, but the operation is not inherently irreversible or financial.
From the tool's definition Tool name 'update_document' clearly indicates modification of stored documents. Server context confirms this is a 'storage and retrieval' system for persistent knowledge base.
Documented attack patterns abuse exactly the kind of access update_document gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Forgetful, and nothing reaches the server without passing your rules. This is the rule we recommend for update_document:
{
"version": "1",
"default": "deny",
"tools": {
"update_document": {
"limits": [
{
"counter": "update_document_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_document 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_document. It is categorised as a Write tool in the Forgetful MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Forgetful MCP server in PolicyLayer and add a rule for update_document: 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 Forgetful. Nothing to install.
update_document 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_document 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_document. 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_document is provided by the Forgetful MCP server (scottrbk/forgetful). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 59 Forgetful tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
59 Forgetful tools catalogued and risk-classified — across an index of 42,500+ MCP servers.