AI agents use set_card_template_tags to create or update resources in Metabase — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Metabase environment.
The tool modifies card template tag configurations, which is a reversible change to metadata/settings within Metabase. This aligns with Write category (create, update, post, upload). Severity is medium because misconfiguration of template tags could affect dashboard behavior or expose unintended data, but changes are reversible.
From the tool's definition Tool name 'set_card_template_tags' indicates modification of template tags on a card (template configuration). Context shows this is a Metabase MCP server managing dashboards, cards, and queries. The 'set' operation implies updating card properties.
Attacks that exploit this kind of access
set_card_template_tags. It is categorised as a Write tool in the Metabase MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Metabase MCP server in PolicyLayer and add a rule for set_card_template_tags: 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 Metabase. Nothing to install.
set_card_template_tags 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 set_card_template_tags 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 set_card_template_tags. 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.
set_card_template_tags is provided by the Metabase MCP server (voducdan/matebase-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 →