AI agents use update_page to create or update resources in Wikidocs — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Wikidocs environment.
The tool modifies existing page content in a reversible manner. This is a Write operation—it creates or modifies data but does not irreversibly delete it. Severity is medium because an agent could misuse it to vandalize or modify pages in ways that harm the wiki's integrity, but changes are typically recoverable through version history or reverting.
From the tool's definition Tool name 'update_page' combined with server description stating it 'enables AI agents to read, edit, and manage Wikidocs books and blogs, including page CRUD operations.' Update is a reversible modification operation (Create, Read, Update, Delete).
Documented attack patterns abuse exactly the kind of access update_page gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Wikidocs, and nothing reaches the server without passing your rules. This is the rule we recommend for update_page:
{
"version": "1",
"default": "deny",
"tools": {
"update_page": {
"limits": [
{
"counter": "update_page_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_page 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_page. It is categorised as a Write tool in the Wikidocs MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Wikidocs MCP server in PolicyLayer and add a rule for update_page: 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 Wikidocs. Nothing to install.
update_page 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_page 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_page. 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_page is provided by the Wikidocs MCP server (ychoi-kr/wikidocs-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Wikidocs, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
17 Wikidocs tools catalogued and risk-classified — across an index of 43,000+ MCP servers.