Preview updates for multiple cards at once.
AI agents use update_cards_batch_preview to create or update resources in Mochi MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mochi MCP Server environment.
The tool performs updates (write operations) on multiple cards, which constitutes data modification. While it is a preview/preparatory step rather than actual application (mitigated by the two-phase commit pattern described in the server), it still represents write-class functionality.
From the tool's definition Tool name contains 'update' and description states 'Preview updates for multiple cards at once.' This is a write operation that modifies card data.
Attacks that exploit this kind of access
Preview updates for multiple cards at once. It is categorised as a Write tool in the Mochi MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mochi MCP Server MCP server in PolicyLayer and add a rule for update_cards_batch_preview: 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 Mochi MCP Server. Nothing to install.
update_cards_batch_preview 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_cards_batch_preview 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_cards_batch_preview. 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_cards_batch_preview is provided by the Mochi MCP Server MCP server (nz99/mochi-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 →