AI agents use archive_card to create or update resources in Codecks — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Codecks environment.
Archiving is a reversible modification to data state—the card is hidden or marked as archived but can be unarchived. This is a write operation (state modification) rather than destructive (permanent deletion). The blast radius is medium because an agent incorrectly archiving cards could disrupt project workflows, but the action can be undone.
From the tool's definition Tool name 'archive_card' and description states it is 'reversible'. Archiving is a state change that modifies a card's visibility/status without permanently deleting data.
Attacks that exploit this kind of access
Archive a card (reversible). It is categorised as a Write tool in the Codecks MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Codecks MCP server in PolicyLayer and add a rule for archive_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 Codecks. Nothing to install.
archive_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 archive_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 archive_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.
archive_card is provided by the Codecks MCP server (rangogamedev/codecks-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 →