Preview changes to specific fields (Question, Answer, Tags). Reconstructs full markdown.
AI agents call update_card_fields_preview to retrieve information from Mochi MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name includes 'preview' and the description states it previews changes without applying them. This is consistent with the server's two-phase commit pattern where preview tools only show intended changes, while 'apply_*' tools perform the actual writes. No data is modified.
From the tool's definition 'Preview changes' and 'Reconstructs full markdown' — this is a preview/read operation that shows what changes would look like without applying them
Attacks that exploit this kind of access
Preview changes to specific fields (Question, Answer, Tags). Reconstructs full markdown. It is categorised as a Read tool in the Mochi MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Mochi MCP Server MCP server in PolicyLayer and add a rule for update_card_fields_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_card_fields_preview is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the update_card_fields_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_card_fields_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_card_fields_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 →