Update a custom view
AI agents use update_view to create or update resources in Fusebase MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Fusebase MCP Server environment.
This tool modifies an existing view, which is a reversible data change operation. It falls under Write rather than Read (which only retrieves) or Destructive (which is irreversible). Severity is medium because updating views could affect data visibility or reporting for multiple users, but the change is non-destructive and typically reversible.
From the tool's definition Tool name is 'update_view' and description states 'Update a custom view'. The verb 'update' indicates modification of existing data (a view configuration) rather than creation, deletion, or execution of arbitrary operations.
Attacks that exploit this kind of access
Update a custom view. It is categorised as a Write tool in the Fusebase MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Fusebase MCP Server MCP server in PolicyLayer and add a rule for update_view: 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 Fusebase MCP Server. Nothing to install.
update_view 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_view 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_view. 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_view is provided by the Fusebase MCP Server MCP server (ryan-haver/fusebase-mcp). 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 →