AI agents use register_script to create or update resources in MCPMake — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCPMake environment.
This is a Write operation because it creates/stores new script data reversibly in a registry. However, severity is elevated to 'high' rather than typical Write 'medium' because: (1) registered scripts can be executed by run_script, making registration a precursor to code execution, (2) malicious script registration could enable arbitrary Python execution, and (3) while the registration itself is reversible (can be…
From the tool's definition Tool description states it registers 'a new Python script', which is a create operation that adds data to the script registry.
Attacks that exploit this kind of access
Register a new Python script with automatic schema extraction. It is categorised as a Write tool in the MCPMake MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCPMake MCP server in PolicyLayer and add a rule for register_script: 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 MCPMake. Nothing to install.
register_script 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 register_script 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 register_script. 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.
register_script is provided by the MCPMake MCP server (shex1627/mcpmake). 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 →