AI agents use tool_create_view to create or update resources in Mcp Excel — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Excel environment.
Creating a view modifies the data environment by adding a new schema object. This is reversible (views can be dropped) and has no financial or destructive impact, making it Write rather than Execute or Destructive. Severity is medium because view creation could affect data analysis workflows and consume resources, but impact is limited to schema structure.
From the tool's definition Tool name 'tool_create_view' indicates creation of a database view, which modifies schema and creates new objects. The server context (Excel/CSV querying via SQL) confirms this creates persistent query definitions.
Attacks that exploit this kind of access
tool_create_view. It is categorised as a Write tool in the Mcp Excel MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Excel MCP server in PolicyLayer and add a rule for tool_create_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 Mcp Excel. Nothing to install.
tool_create_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 tool_create_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 tool_create_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.
tool_create_view is provided by the Mcp Excel MCP server (ivan-loh/mcp-excel). 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 →