Preview removing tags from one or more cards. Returns a token for apply_tags_update.
AI agents call remove_tags_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 explicitly performs a preview operation, meaning it reads and computes what would happen without making any modifications. It returns a token used by a separate apply tool, making this a read-only staging step with no side effects.
From the tool's definition 'Preview removing tags from one or more cards. Returns a token for apply_tags_update.' — this is a preview/dry-run step that does not apply changes, only prepares a token for a subsequent apply step.
Attacks that exploit this kind of access
Preview removing tags from one or more cards. Returns a token for apply_tags_update. 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 remove_tags_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.
remove_tags_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 remove_tags_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 remove_tags_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.
remove_tags_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 →