add_top_level
AI agents use add_top_level to create or update resources in Ast Editor — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ast Editor environment.
This tool appears to add top-level declarations or imports to code files. Adding top-level code elements is a Write operation—it modifies code reversibly (can be undone/removed). It does not delete data (Destructive), execute arbitrary code (Execute), or move money (Financial).
From the tool's definition Tool name 'add_top_level' combined with sibling tools like 'add_field', 'add_import', 'add_method', and 'add_parameter' indicates creation/modification of code structures.
Attacks that exploit this kind of access
add_top_level. It is categorised as a Write tool in the Ast Editor MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ast Editor MCP server in PolicyLayer and add a rule for add_top_level: 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 Ast Editor. Nothing to install.
add_top_level 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 add_top_level 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 add_top_level. 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.
add_top_level is provided by the Ast Editor MCP server (kambleakash0/ast-editor). 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 →