Toggle a tag on a Fizzy card. If the tag is not on the card, it will be added. If it is, it will be removed.
AI agents use fizzy_tag_card to create or update resources in Fizzy MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Fizzy MCP Server environment.
This tool modifies card metadata (tags) in a reversible way — tags can be re-added or removed again at any time. It neither deletes data irreversibly nor executes code, making Write the appropriate category. The blast radius is low since only tag metadata is affected.
From the tool's definition Toggle a tag on a Fizzy card. If the tag is not on the card, it will be added. If it is, it will be removed.
Attacks that exploit this kind of access
Toggle a tag on a Fizzy card. If the tag is not on the card, it will be added. If it is, it will be removed. It is categorised as a Write tool in the Fizzy MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Fizzy MCP Server MCP server in PolicyLayer and add a rule for fizzy_tag_card: 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 Fizzy MCP Server. Nothing to install.
fizzy_tag_card 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 fizzy_tag_card 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 fizzy_tag_card. 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.
fizzy_tag_card is provided by the Fizzy MCP Server MCP server (ryanyogan/fizzy-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 →