AI agents use codemagic_add_application to create or update resources in Codemagic — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Codemagic environment.
An AI agent can call codemagic_add_application faster than any human can review — one bad instruction and it creates or modifies resources in Codemagic by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Add a new application to Codemagic from a public Git repository. For private repos use codemagic_add_application_private instead. It is categorised as a Write tool in the Codemagic MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Codemagic MCP server in PolicyLayer and add a rule for codemagic_add_application: 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 Codemagic. Nothing to install.
codemagic_add_application 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 codemagic_add_application 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 codemagic_add_application. 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.
codemagic_add_application is provided by the Codemagic MCP server (zfinix/codemagic_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.