Update an existing site. All fields are optional — only provided fields are changed. Links replace the entire array (omit to keep existing). Before updating, always call unulu_get_state first to read the current links and their ids — do not guess link ids. Authorization depends on site lifecycle:...
Risk signalsAccepts URL/endpoint input (links[].url) · High parameter count (16 properties) · Bulk/mass operation — affects multiple targets
Part of the Unulu server.
Free to start. No card required.
AI agents use unulu_update_site to create or modify resources in Unulu. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call unulu_update_site repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Unulu.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"unulu_update_site": {
"limits": [
{
"counter": "unulu_update_site_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full Unulu policy for all 4 tools.
These attack patterns abuse exactly the kind of access unulu_update_site gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Update an existing site. All fields are optional — only provided fields are changed. Links replace the entire array (omit to keep existing). Before updating, always call unulu_get_state first to read the current links and their ids — do not guess link ids. Authorization depends on site lifecycle: X-Claim-Token header for ephemeral (pre-claim) sites, X-Edit-Token header for claimed (post-claim) sites. If neither token is available and the site is claimed, use requestEditAccess to obtain an edit_token. If you created the site in this conversation, you already have the claim_token — use it directly. Returns the full updated site state. Keep iteration fast — apply changes immediately without re-confirming minor edits unless ambiguous. Accepts a site ID, a full URL (e.g. https://abc123.unu.lu), or a bare hostname (e.g. abc123.unu.lu).. It is categorised as a Write tool in the Unulu MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Unulu MCP server in PolicyLayer and add a rule for unulu_update_site: 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 Unulu. Nothing to install.
unulu_update_site 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 unulu_update_site 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 unulu_update_site. 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.
unulu_update_site is provided by the Unulu MCP server (https://mcp.unulu.ai). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 Unulu tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.