AI agents use split_features 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.
The tool creates/modifies data structure by splitting cards into sub-cards. This is a Write operation rather than Execute because it performs a specific data transformation operation on project management entities rather than arbitrary code execution.
From the tool's definition Tool description states it performs batch-split operations on feature cards into lane sub-cards. This is a modification operation that creates new sub-cards from existing cards, which is reversible.
Attacks that exploit this kind of access
Batch-split unsplit feature cards into lane sub-cards. Use dry_run=true to preview. 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 split_features: 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.
split_features 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 split_features 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 split_features. 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.
split_features 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 →