nc_auth_update_scopes
AI agents use nc_auth_update_scopes to create or update resources in Nextcloud MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nextcloud MCP Server environment.
Updating OAuth scopes modifies security permissions and access rights to Nextcloud resources (Notes, Calendar, Contacts, Files, Deck, Cookbook, Tables). This is a reversible Write operation that changes system state (access grants). It is not Destructive (scopes can be updated again), not Execute (doesn't run arbitrary code), and not Financial.
From the tool's definition Tool name 'nc_auth_update_scopes' indicates modification of OAuth2 authorization scopes, which alters access permissions. The description is empty, limiting confidence.
Attacks that exploit this kind of access
nc_auth_update_scopes. It is categorised as a Write tool in the Nextcloud MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nextcloud MCP Server MCP server in PolicyLayer and add a rule for nc_auth_update_scopes: 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 Nextcloud MCP Server. Nothing to install.
nc_auth_update_scopes 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 nc_auth_update_scopes 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 nc_auth_update_scopes. 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.
nc_auth_update_scopes is provided by the Nextcloud MCP Server MCP server (no-smoke/nextcloud-mcp-comprehensive). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →