add_card
AI agents use add_card to create or update resources in FlashCardsMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your FlashCardsMCP environment.
The tool name 'add_card' explicitly indicates a creation operation. Within the context of a flash card project manager backed by SQLite, this operation modifies the database by inserting new records. This is a reversible Write action (cards can be deleted or updated later), not Destructive. It does not execute arbitrary code, move money, or merely read data.
From the tool's definition Tool is named 'add_card' and belongs to a flash card management system that persists data to SQLite. The sibling tools reveal this server creates, retrieves, and searches cards.
Attacks that exploit this kind of access
add_card. It is categorised as a Write tool in the FlashCardsMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the FlashCards MCP server in PolicyLayer and add a rule for add_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 FlashCardsMCP. Nothing to install.
add_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 add_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 add_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.
add_card is provided by the FlashCards MCP server (mtib/flash-cards-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 →