AI agents use remove_from_hand 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.
Removing a card from a user's 'hand' in Codecks is a reversible write operation - the card still exists and can be re-added. This is not destructive as the card itself is not deleted. The sibling tool 'add_to_hand' confirms this is a paired reversible operation. Confidence is moderate because the description is very brief and doesn't fully explain the operation.
From the tool's definition 'Remove cards from the user' suggests removing a card association from a user's hand (a project management concept), which is a reversible modification
Attacks that exploit this kind of access
Remove cards from the user. 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 remove_from_hand: 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.
remove_from_hand 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 remove_from_hand 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_from_hand. 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_from_hand 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 →